Intern

Data Science Chair

Dr. Daniel Schlör

Chair of Data Science (Informatik X)
University of Würzburg
Campus Hubland Nord
Emil-Fischer-Straße 50
97074 Würzburg
Germany

Email: daniel.schloer[at]informatik.uni-wuerzburg.de

Phone: (+49 931) 31 - 84564

Office: Room 50.03.017 (Institutsgebäude Künstliche Intelligenz)

Projects and Research Interests

My main research interests are machine learning, anomaly detection and natural language processing in the fields of cybersecurity and fraud detection. Currently I'm working on deep learning models able to capture domain specific relationships within data.

In addition to my affiliation with the Data Science chair, I have been a member of the CLiGS – Computational Literary Genre Stylistics research group, working in the field of Digital Humanities.

Teaching

Winter term 24/25: Anomaly Detection
Winter term 24/25: Grundlagen der Algorithmen und Datenstrukturen
Summer term 24: Seminar + Praktikum: Machine Learning for Cyber Security
Summer term 24: Vorlesung zu Data Science (ehemals Data Mining)
Winter term 23/24: Vorlesung zu Machine Learning for Time Series and Anomaly Detection
Summer term 23: Übung zu Music Information Retrieval
Summer term 23: Seminar: Ausgewählte Themen des Machine Learning (BA and MA)
Winter term 22/23: Seminar: Ausgewählte Themen des Machine Learning (BA and MA)
Summer term 21: Praktikum: Musik und Maschinelles Lernen
Winter term 20/21: Übung zu Grundlagen der Algorithmen und Datenstrukturen
Winter term 20/21: Seminar: Musik und Maschinelles Lernen
Winter term 19/20: Übung zu Grundlagen der Algorithmen und Datenstrukturen
Winter term 18/19: Übung zu Grundlagen der Algorithmen und Datenstrukturen
Winter term 17/18: Übung zu Grundlagen der Algorithmen und Datenstrukturen
Winter term 16/17: Sprachverarbeitung und Text Mining
Winter term 15/16: Sprachverarbeitung und Text Mining

Publications

2025[ to top ]

Röchner, P., Klüttermann, S., Rothlauf, F., and Schlör, D. (2025) “We Need to Rethink Benchmarking in Anomaly Detection”.
- [ BibTeX ]
- [ Download ]
@article{noauthororeditor, author = {Röchner, Philipp and Klüttermann, Simon and Rothlauf, Franz and Schlör, Daniel}, keywords = {position}, title = {We Need to Rethink Benchmarking in Anomaly Detection}, year = 2025 }

2024[ to top ]

Hesselbach, R., Calvo Tello, J., Henny-Krahmer, U., Schöch, C., and Schlör, D. (2024) “Digital Stylistics in Romance Studies and Beyond”.
- [ BibTeX ]
- [ Download ]
@misc{hesselbach2024digital, author = {Hesselbach, Robert and Calvo Tello, Jos{\'e} and Henny-Krahmer, Ulrike and Schöch, Christof and Schlör, Daniel}, keywords = {dh}, publisher = {Heidelberg University Publishing (heiUP)}, title = {Digital Stylistics in Romance Studies and Beyond}, year = 2024 }
Wolf, M., Landes, D., Hotho, A., and Schlör, D. (2024) “Systematic Evaluation of Synthetic Data Augmentation for Multi-class NetFlow Traffic.”, CoRR, abs/2408.16034, available: http://dblp.uni-trier.de/db/journals/corr/corr2408.html#abs-2408-16034.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@article{journals/corr/abs-2408-16034, author = {Wolf, Maximilian and Landes, Dieter and Hotho, Andreas and Schlör, Daniel}, journal = {CoRR}, keywords = {author:hotho}, title = {Systematic Evaluation of Synthetic Data Augmentation for Multi-class NetFlow Traffic.}, volume = {abs/2408.16034}, year = 2024 }
Schaller, M., Schl{{ö}}r, D., and Hotho, A. (2024) “ModeConv: {A} Novel Convolution for Distinguishing Anomalous and Normal Structural Behavior”, CoRR, abs/2407.00140, available: https://doi.org/10.48550/ARXIV.2407.00140.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@article{schaller2024modeconv, author = {Schaller, Melanie and Schl{\"{o}}r, Daniel and Hotho, Andreas}, journal = {CoRR}, keywords = 2024, title = {ModeConv: {A} Novel Convolution for Distinguishing Anomalous and Normal Structural Behavior}, volume = {abs/2407.00140}, year = 2024 }
Wolf, M., Tritscher, J., Landes, D., Hotho, A., and Schlör, D. (2024) “Benchmarking of synthetic network data: Reviewing challenges and approaches.”, Computers and Security, 145, 103993, available: http://dblp.uni-trier.de/db/journals/compsec/compsec145.html#WolfTLHS24.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@article{journals/compsec/WolfTLHS24, author = {Wolf, Maximilian and Tritscher, Julian and Landes, Dieter and Hotho, Andreas and Schlör, Daniel}, journal = {Computers and Security}, keywords = {author:hotho}, pages = 103993, title = {Benchmarking of synthetic network data: Reviewing challenges and approaches.}, volume = 145, year = 2024 }
Omeliyanenko, J., Hotho, A., and Schlör, D. (2024) “PreAdapter: Pre-training Language Models on Knowledge Graphs”, International Semantic Web Conference ISWC 2024, to appear.
- [ BibTeX ]
- [ Download ]
@article{omeliyanenko2024preadapter, author = {Omeliyanenko, Janna and Hotho, Andreas and Schlör, Daniel}, journal = {International Semantic Web Conference ISWC 2024, to appear}, keywords = {graph}, title = {PreAdapter: Pre-training Language Models on Knowledge Graphs}, year = 2024 }
Tritscher, J., Wolf, M., Krause, A., Hotho, A., and Schlör, D. (2024) “Data Generation for Explainable Occupational Fraud Detection”, 47th German Conference on Artificial Intelligence (KI 2024) - to appear.
- [ Abstract ]
- [ BibTeX ]
- [ Download ]
Occupational fraud, the deliberate misuse of company assets by employees, causes damages of around 5% of yearly company revenue. Recent work therefore focuses on automatically detecting occupational fraud through machine learning on the company data contained within enterprise resource planning systems. Since interpretability of these machine learning approaches is considered a relevant aspect of occupational fraud detection, first works have already integrated post-hoc explainable artificial intelligence approaches into their fraud detectors. While these explainers show promising first results, systematic advancement of explainable fraud detection methods is currently hindered by the general lack of ground truth explanations to evaluate explanation quality and choose suitable explainers. To avoid expensive expert annotations, we propose a data generation scheme based on multi-agent systems to obtain company data with labeled occupational fraud cases and ground truth explanations. Using this data generator, we design a framework that enables the optimization of post-hoc explainers for unlabeled company data. On two datasets, we experimentally show that our framework is able to successfully differentiate between explainers of high and low explanation quality, showcasing the potential of multi-agent-simulations to ensure proper performance of post-hoc explainers.

@article{tritscher2024generation, abstract = {Occupational fraud, the deliberate misuse of company assets by employees, causes damages of around 5% of yearly company revenue. Recent work therefore focuses on automatically detecting occupational fraud through machine learning on the company data contained within enterprise resource planning systems. Since interpretability of these machine learning approaches is considered a relevant aspect of occupational fraud detection, first works have already integrated post-hoc explainable artificial intelligence approaches into their fraud detectors. While these explainers show promising first results, systematic advancement of explainable fraud detection methods is currently hindered by the general lack of ground truth explanations to evaluate explanation quality and choose suitable explainers. To avoid expensive expert annotations, we propose a data generation scheme based on multi-agent systems to obtain company data with labeled occupational fraud cases and ground truth explanations. Using this data generator, we design a framework that enables the optimization of post-hoc explainers for unlabeled company data. On two datasets, we experimentally show that our framework is able to successfully differentiate between explainers of high and low explanation quality, showcasing the potential of multi-agent-simulations to ensure proper performance of post-hoc explainers.}, author = {Tritscher, Julian and Wolf, Maximilian and Krause, Anna and Hotho, Andreas and Schlör, Daniel}, journal = {47th German Conference on Artificial Intelligence (KI 2024) - to appear}, keywords = {xai}, title = {Data Generation for Explainable Occupational Fraud Detection}, year = 2024 }
Schl{ö}r, D. and Hotho, A. (2024) “Verantwortungsvolle Empfehlungssysteme f{ü}r die medizinische Diagnostik”, Edition Moderne Postmoderne, 101.
- [ BibTeX ]
- [ Download ]
@article{schlorverantwortungsvolle, author = {Schl{\"o}r, Daniel and Hotho, Andreas}, journal = {Edition Moderne Postmoderne}, keywords = {ai}, pages = 101, title = {Verantwortungsvolle Empfehlungssysteme f{\"u}r die medizinische Diagnostik}, year = 2024 }
Tritscher, J., Lissmann, P., Wolf, M., Krause, A., Hotho, A., and Schlör, D. (2024) “Generative Inpainting for Shapley-Value-Based Anomaly Explanation”, The World Conference on eXplainable Artificial Intelligence (xAI 2024).
- [ Abstract ]
- [ BibTeX ]
- [ Download ]
Feature relevance explanations currently constitute the most used type of explanation in anomaly detection related tasks such as cyber security and fraud detection. Recent works have underscored the importance of optimizing hyperparameters of post-hoc explainers which show a large impact on the resulting explanation quality. In this work, we propose a new method to set the hyperparameter of replacement values within Shapley-value-based post-hoc explainers. Our method leverages ideas from the domain of generative image inpainting, where generative machine learning models are used to replace parts of a given input image. We show that these generative models can also be applied to tabular replacement value generation for Shapley-value-based feature relevance explainers. Experimentally, we train a denoising diffusion probabilistic model for generative inpainting on two tabular anomaly detection datasets from the domains of network intrusion detection and occupational fraud detection, and integrate the generative inpainting model into the SHAP explanation framework. We empirically show that generative inpainting may be used to achieve consistently strong explanation quality when explaining different anomaly detectors on tabular data.

@article{noauthororeditor, abstract = {Feature relevance explanations currently constitute the most used type of explanation in anomaly detection related tasks such as cyber security and fraud detection. Recent works have underscored the importance of optimizing hyperparameters of post-hoc explainers which show a large impact on the resulting explanation quality. In this work, we propose a new method to set the hyperparameter of replacement values within Shapley-value-based post-hoc explainers. Our method leverages ideas from the domain of generative image inpainting, where generative machine learning models are used to replace parts of a given input image. We show that these generative models can also be applied to tabular replacement value generation for Shapley-value-based feature relevance explainers. Experimentally, we train a denoising diffusion probabilistic model for generative inpainting on two tabular anomaly detection datasets from the domains of network intrusion detection and occupational fraud detection, and integrate the generative inpainting model into the SHAP explanation framework. We empirically show that generative inpainting may be used to achieve consistently strong explanation quality when explaining different anomaly detectors on tabular data.}, author = {Tritscher, Julian and Lissmann, Philip and Wolf, Maximilian and Krause, Anna and Hotho, Andreas and Schlör, Daniel}, journal = {The World Conference on eXplainable Artificial Intelligence (xAI 2024)}, keywords = {xai}, title = {Generative Inpainting for Shapley-Value-Based Anomaly Explanation}, year = 2024 }
Fischer, E., Zehe, A., Hotho, A., and Schlör, D. (2024) “Modeling and Analyzing the Influence of Non-Item Pages on Sequential Next-Item Prediction”, available: https://arxiv.org/abs/2408.15953.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@misc{fischer2024modeling, author = {Fischer, Elisabeth and Zehe, Albin and Hotho, Andreas and Schlör, Daniel}, keywords = {author:zehe}, month = 10, title = {Modeling and Analyzing the Influence of Non-Item Pages on Sequential Next-Item Prediction}, year = 2024 }

2023[ to top ]

Schaller, M., Steininger, M., Dulny, A., Schlör, D., and Hotho, A. (2023) “Liquor-HGNN: A heterogeneous graph neural network for leakage detection in water distribution networks”, LWDA’23: Lernen, Wissen, Daten, Analysen. October 09--11, 2023, Marburg, Germany.
- [ BibTeX ]
@article{schaller2023liquorhgnn, author = {Schaller, Melanie and Steininger, Michael and Dulny, Andrzej and Schlör, Daniel and Hotho, Andreas}, editor = {Leyer, M.}, journal = {LWDA'23: Lernen, Wissen, Daten, Analysen. October 09–11, 2023, Marburg, Germany}, keywords = {cps}, month = {Oktober}, title = {Liquor-HGNN: A heterogeneous graph neural network for leakage detection in water distribution networks}, year = 2023 }
Tritscher, J., Roos, A., Schlör, D., Hotho, A., and Krause, A. (2023) “Occupational Fraud Detection through Agent-based Data Generation”, The 8th Workshop on MIning DAta for financial applicationS MIDAS 2023 - to appear.
- [ Abstract ]
- [ BibTeX ]
Occupational fraud is an increasing concern for enterprises that is estimated to cause losses of around 5% of company revenue each year. With the increasing data tracked by companies through enterprise resource planning systems, recent research has taken interest in the automated detection of occupational fraud. Automated detection is however hindered by the unavailability of labeled fraud cases which require known occupational frauds within company data and costly expert annotation. Even despite the existence of anomaly detection methods that can be trained on unsupervised data, selecting the ideal preprocessing techniques, the most suitable model, and the optimal hyperparameters necessitates the availability of labeled data for evaluation purposes. To alleviate this issue, we propose to use simulation through multi-agent systems for generating business processes according to best practices from economics and creating labeled synthetic data that closely matches a given unlabeled real-world dataset. We extend an existing simulation by incorporating functionality for including, tracking and automatic labeling of occupational fraud cases. Using this simulation, we propose a framework that decides on important design choices for fraud detection models in enterprise resource planning data and does not require labeled real-world data. We demonstrate in multiple experiments that the framework can aid automated occupational fraud detection through data generation.

@article{tritscher2023occupational, abstract = {Occupational fraud is an increasing concern for enterprises that is estimated to cause losses of around 5% of company revenue each year. With the increasing data tracked by companies through enterprise resource planning systems, recent research has taken interest in the automated detection of occupational fraud. Automated detection is however hindered by the unavailability of labeled fraud cases which require known occupational frauds within company data and costly expert annotation. Even despite the existence of anomaly detection methods that can be trained on unsupervised data, selecting the ideal preprocessing techniques, the most suitable model, and the optimal hyperparameters necessitates the availability of labeled data for evaluation purposes. To alleviate this issue, we propose to use simulation through multi-agent systems for generating business processes according to best practices from economics and creating labeled synthetic data that closely matches a given unlabeled real-world dataset. We extend an existing simulation by incorporating functionality for including, tracking and automatic labeling of occupational fraud cases. Using this simulation, we propose a framework that decides on important design choices for fraud detection models in enterprise resource planning data and does not require labeled real-world data. We demonstrate in multiple experiments that the framework can aid automated occupational fraud detection through data generation.}, author = {Tritscher, Julian and Roos, Alexander and Schlör, Daniel and Hotho, Andreas and Krause, Anna}, journal = {The 8th Workshop on MIning DAta for financial applicationS MIDAS 2023 - to appear}, keywords = {mas}, title = {Occupational Fraud Detection through Agent-based Data Generation}, year = 2023 }
Tritscher, J., Wolf, M., Hotho, A., and Schlör, D. (2023) “Evaluating feature relevance XAI in network intrusion detection”, The World Conference on eXplainable Artificial Intelligence (xAI 2023) - to appear.
- [ Abstract ]
- [ BibTeX ]
As machine learning models become increasingly complex, there is a growing need for explainability to understand and trust the decision-making processes. In the domain of network intrusion detection, post-hoc feature relevance explanations have been widely used to provide insight into the factors driving model decisions. However, recent research has highlighted challenges with these methods when applied to anomaly detection, which can vary in importance and impact depending on the application domain. In this paper, we investigate the challenges of post-hoc feature relevance explanations for network intrusion detection, a critical area for ensuring the security and integrity of computer networks. To gain a deeper understanding of these challenges for the application domain, we quantitatively and qualitatively investigate the popular feature relevance approach SHAP when explaining different network intrusion detection approaches. We conduct experiments to jointly evaluate detection quality and explainability, and explore the impact of replacement data, a commonly overlooked hyperparameter of post-hoc feature relevance approaches. We find that post-hoc XAI can provide high quality explanations, but requires a careful choice of its replacement data as default settings and common choices do not transfer across different detection models. Our study showcases the viability of post-hoc XAI for network intrusion detection systems, but highlights the need for rigorous evaluations of produced explanations.

@article{tritscher2023evaluating, abstract = {As machine learning models become increasingly complex, there is a growing need for explainability to understand and trust the decision-making processes. In the domain of network intrusion detection, post-hoc feature relevance explanations have been widely used to provide insight into the factors driving model decisions. However, recent research has highlighted challenges with these methods when applied to anomaly detection, which can vary in importance and impact depending on the application domain. In this paper, we investigate the challenges of post-hoc feature relevance explanations for network intrusion detection, a critical area for ensuring the security and integrity of computer networks. To gain a deeper understanding of these challenges for the application domain, we quantitatively and qualitatively investigate the popular feature relevance approach SHAP when explaining different network intrusion detection approaches. We conduct experiments to jointly evaluate detection quality and explainability, and explore the impact of replacement data, a commonly overlooked hyperparameter of post-hoc feature relevance approaches. We find that post-hoc XAI can provide high quality explanations, but requires a careful choice of its replacement data as default settings and common choices do not transfer across different detection models. Our study showcases the viability of post-hoc XAI for network intrusion detection systems, but highlights the need for rigorous evaluations of produced explanations.}, author = {Tritscher, Julian and Wolf, Maximilian and Hotho, Andreas and Schlör, Daniel}, journal = {The World Conference on eXplainable Artificial Intelligence (xAI 2023) - to appear}, keywords = {xai}, title = {Evaluating feature relevance XAI in network intrusion detection}, year = 2023 }
Omeliyanenko, J., Zehe, A., Hotho, A., and Schlör, D. (2023) “CapsKG: Enabling Continual Knowledge Integration in Language Models for Automatic Knowledge Graph Completion”, International Semantic Web Conference ISWC 2023, to appear.
- [ Abstract ]
- [ BibTeX ]
Automated completion of knowledge graphs is a popular topic in the Semantic Web community that aims to automatically and continuously integrate new appearing knowledge into knowledge graphs using artificial intelligence. Recently, approaches that leverage implicit knowledge from language models for this task have shown promising re- sults. However, by fine-tuning language models directly to the domain of knowledge graphs, models forget their original language representation and associated knowledge. An existing solution to address this issue is a trainable adapter, which is integrated into a frozen language model to extract the relevant knowledge without altering the model itself. How- ever, this constrains the generalizability to the specific extraction task and by design requires new and independent adapters to be trained for new knowledge extraction tasks. This effectively prevents the model from benefiting from existing knowledge incorporated in previously trained adapters. In this paper, we propose to combine the benefits of adapters for knowl- edge graph completion with the idea of integrating capsules, introduced in the field of continual learning. This allows the continuous integra- tion of knowledge into a joint model by sharing and reusing previously trained capsules. We find that our approach outperforms solutions using traditional adapters, while requiring notably fewer parameters for con- tinuous knowledge integration. Moreover, we show that this architecture benefits significantly from knowledge sharing in low-resource situations, outperforming adapter-based models on the task of link prediction.

@article{noauthororeditor, abstract = {Automated completion of knowledge graphs is a popular topic in the Semantic Web community that aims to automatically and continuously integrate new appearing knowledge into knowledge graphs using artificial intelligence. Recently, approaches that leverage implicit knowledge from language models for this task have shown promising re- sults. However, by fine-tuning language models directly to the domain of knowledge graphs, models forget their original language representation and associated knowledge. An existing solution to address this issue is a trainable adapter, which is integrated into a frozen language model to extract the relevant knowledge without altering the model itself. How- ever, this constrains the generalizability to the specific extraction task and by design requires new and independent adapters to be trained for new knowledge extraction tasks. This effectively prevents the model from benefiting from existing knowledge incorporated in previously trained adapters. In this paper, we propose to combine the benefits of adapters for knowl- edge graph completion with the idea of integrating capsules, introduced in the field of continual learning. This allows the continuous integra- tion of knowledge into a joint model by sharing and reusing previously trained capsules. We find that our approach outperforms solutions using traditional adapters, while requiring notably fewer parameters for con- tinuous knowledge integration. Moreover, we show that this architecture benefits significantly from knowledge sharing in low-resource situations, outperforming adapter-based models on the task of link prediction.}, author = {Omeliyanenko, Janna and Zehe, Albin and Hotho, Andreas and Schlör, Daniel}, journal = {International Semantic Web Conference ISWC 2023, to appear}, keywords = {kg}, title = {CapsKG: Enabling Continual Knowledge Integration in Language Models for Automatic Knowledge Graph Completion}, year = 2023 }
Fischer, E., Schlör, D., Zehe, A., and Hotho, A. (2023) “Enhancing Sequential Next-Item Prediction through Modelling Non-Item Pages”.
- [ BibTeX ]
@unpublished{fischer2023enhancing, author = {Fischer, Elisabeth and Schlör, Daniel and Zehe, Albin and Hotho, Andreas}, keywords = {reco}, title = {Enhancing Sequential Next-Item Prediction through Modelling Non-Item Pages}, year = 2023 }
Schlör, D., Pfister, J., and Hotho, A. (2023) “Optimizing Medical Service Request Processes through Language Modeling and Semantic Search”, in 2023 the 7th International Conference on Medical and Health Informatics (ICMHI), ICMHI 2023, Kyoto, Japan: Association for Computing Machinery, 136–141, available: https://doi.org/10.1145/3608298.3608324.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
Medical service requests are a crucial part of the workflow in hospitals and healthcare organizations. However, the process of requesting medical services can be time consuming and can require physicians and medical personnel to navigate complex interfaces and enter detailed information about the requested service. In this paper, we propose a system that uses machine learning techniques such as large language models and semantic search to optimize the process of requesting medical services. Our approach enables physicians to request medical services using natural language rather than navigating complex interfaces, allowing for more efficient and flexible interactions with hospital information systems. We evaluate our approach on real-world data and discuss the implications of our work for the future of digital health care. Our results suggest that our approach has the potential to streamline the process of requesting medical services and reduce the time and manual effort required in the daily hospital routine.

@inproceedings{10.1145/3608298.3608324, abstract = {Medical service requests are a crucial part of the workflow in hospitals and healthcare organizations. However, the process of requesting medical services can be time consuming and can require physicians and medical personnel to navigate complex interfaces and enter detailed information about the requested service. In this paper, we propose a system that uses machine learning techniques such as large language models and semantic search to optimize the process of requesting medical services. Our approach enables physicians to request medical services using natural language rather than navigating complex interfaces, allowing for more efficient and flexible interactions with hospital information systems. We evaluate our approach on real-world data and discuss the implications of our work for the future of digital health care. Our results suggest that our approach has the potential to streamline the process of requesting medical services and reduce the time and manual effort required in the daily hospital routine.}, address = {New York, NY, USA}, author = {Schlör, Daniel and Pfister, Jan and Hotho, Andreas}, booktitle = {2023 the 7th International Conference on Medical and Health Informatics (ICMHI)}, keywords = {medical}, pages = {136–141}, publisher = {Association for Computing Machinery}, series = {ICMHI 2023}, title = {Optimizing Medical Service Request Processes through Language Modeling and Semantic Search}, year = 2023 }

2022[ to top ]

Schlör, D. and Hotho, A. (2022) “Towards Responsible Medical Diagnostics Recommendation Systems”, available: http://arxiv.org/abs/2209.03760.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
The early development and deployment of hospital and healthcare information systems have encouraged the ongoing digitization of processes in hospitals. Many of these processes, which previously required paperwork and telephone arrangements, are now integrated into IT solutions and require physicians and medical staff to interact with appropriate interfaces and tools. Although this shift to digital data management and process support has benefited patient care in many ways, it requires physicians to accurately capture all relevant information digitally for billing and documentation purposes, which takes a lot of time away from actual patient care work. However, systematic collection of healthcare data over a long period of time offers opportunities to improve this process and support medical staff by introducing recommender systems. Based on a practical working example, in this position paper, we will outline the design of a responsible recommender system in the medical context from a technical, application driven perspective and discuss potential design choices and criteria with a specific focus on accountability, safety, and fairness.

@misc{schlor2022towards, abstract = {The early development and deployment of hospital and healthcare information systems have encouraged the ongoing digitization of processes in hospitals. Many of these processes, which previously required paperwork and telephone arrangements, are now integrated into IT solutions and require physicians and medical staff to interact with appropriate interfaces and tools. Although this shift to digital data management and process support has benefited patient care in many ways, it requires physicians to accurately capture all relevant information digitally for billing and documentation purposes, which takes a lot of time away from actual patient care work. However, systematic collection of healthcare data over a long period of time offers opportunities to improve this process and support medical staff by introducing recommender systems. Based on a practical working example, in this position paper, we will outline the design of a responsible recommender system in the medical context from a technical, application driven perspective and discuss potential design choices and criteria with a specific focus on accountability, safety, and fairness.}, author = {Schlör, Daniel and Hotho, Andreas}, keywords = {ethical}, note = {cite arxiv:2209.03760Comment: 4th FAccTRec Workshop on Responsible Recommendation}, title = {Towards Responsible Medical Diagnostics Recommendation Systems}, year = 2022 }
Tritscher, J., Gwinner, F., Schlör, D., Krause, A., and Hotho, A. (2022) “Open ERP System Data For Occupational Fraud Detection”, available: http://arxiv.org/abs/2206.04460.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
Recent estimates report that companies lose 5% of their revenue to occupational fraud. Since most medium-sized and large companies employ Enterprise Resource Planning (ERP) systems to track vast amounts of information regarding their business process, researchers have in the past shown interest in automatically detecting fraud through ERP system data. Current research in this area, however, is hindered by the fact that ERP system data is not publicly available for the development and comparison of fraud detection methods. We therefore endeavour to generate public ERP system data that includes both normal business operation and fraud. We propose a strategy for generating ERP system data through a serious game, model a variety of fraud scenarios in cooperation with auditing experts, and generate data from a simulated make-to-stock production company with multiple research participants. We aggregate the generated data into ready to used datasets for fraud detection in ERP systems, and supply both the raw and aggregated data to the general public to allow for open development and comparison of fraud detection approaches on ERP system data.

@misc{tritscher2022system, abstract = {Recent estimates report that companies lose 5% of their revenue to occupational fraud. Since most medium-sized and large companies employ Enterprise Resource Planning (ERP) systems to track vast amounts of information regarding their business process, researchers have in the past shown interest in automatically detecting fraud through ERP system data. Current research in this area, however, is hindered by the fact that ERP system data is not publicly available for the development and comparison of fraud detection methods. We therefore endeavour to generate public ERP system data that includes both normal business operation and fraud. We propose a strategy for generating ERP system data through a serious game, model a variety of fraud scenarios in cooperation with auditing experts, and generate data from a simulated make-to-stock production company with multiple research participants. We aggregate the generated data into ready to used datasets for fraud detection in ERP systems, and supply both the raw and aggregated data to the general public to allow for open development and comparison of fraud detection approaches on ERP system data.}, author = {Tritscher, Julian and Gwinner, Fabian and Schlör, Daniel and Krause, Anna and Hotho, Andreas}, keywords = {ERP}, note = {cite arxiv:2206.04460}, title = {Open ERP System Data For Occupational Fraud Detection}, year = 2022 }
Schlör, D. (2022) Detecting Anomalies in Transaction Data, PhD dissertation, available: https://doi.org/10.25972/OPUS-29856.
- [ BibTeX ]
@phdthesis{Schloer2022, author = {Schlör, Daniel}, keywords = {diss}, school = {Universität Würzburg}, title = {Detecting Anomalies in Transaction Data}, type = {Doctoral Thesis}, year = 2022 }
Schlör, D. and Hotho, A. (2022) “Towards Responsible Medical Diagnostics Recommendation Systems”, CoRR, abs/2209.03760, available: https://doi.org/10.48550/arXiv.2209.03760.
- [ BibTeX ]
- [ URL ]
@article{DBLP:journals/corr/abs-2209-03760, author = {Schlör, Daniel and Hotho, Andreas}, journal = {CoRR}, keywords = {reco}, title = {Towards Responsible Medical Diagnostics Recommendation Systems}, volume = {abs/2209.03760}, year = 2022 }

2021[ to top ]

Tritscher, J., Krause, A., Schlör, D., Gwinner, F., Von Mammen, S., and Hotho, A. (2021) “A financial game with opportunities for fraud”, in 2021 IEEE Conference on Games (CoG), 1–5, available: https://doi.org/10.1109/CoG52621.2021.9619070.
- [ BibTeX ]
- [ URL ]
@inproceedings{Tritscher:2021aa, author = {Tritscher, Julian and Krause, Anna and Schlör, Daniel and Gwinner, Fabian and Von Mammen, Sebastian and Hotho, Andreas}, booktitle = {2021 IEEE Conference on Games (CoG)}, keywords = {myown}, pages = {1-5}, title = {A financial game with opportunities for fraud}, year = 2021 }
Ring, M., Schlör, D., Wunderlich, S., Landes, D., and Hotho, A. (2021) “Malware detection on windows audit logs using LSTMs”, Computers & Security, 109, 102389, available: https://doi.org/https://doi.org/10.1016/j.cose.2021.102389.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
Malware is a constant threat and is continuously evolving. Security systems try to keep up with the constant change. One challenge that arises is the large amount of logs generated on an operating system and the need to clarify which information contributes to the detection of possible malware. This work aims at the detection of malware using neural networks based on Windows audit log events. Neural networks can only process continuous data, but Windows audit logs are sequential and textual data. To address these challenges, we extract features out of the audit log events and use LSTMs to capture sequential effects. We create different subsets of features and analyze the effects of additional information. Features describe for example the action-type of windows audit log events, process names or target files that are accessed. Textual features are represented either as one-hot encoding or embedding representation, for which we compare three different approaches for representation learning. Effects of different feature subsets and representations are evaluated on a publicly available data set. Results indicate that using additional information improves the performance of the LSTM-model. While different representations lead to similar classification results, analysis of the latent space shows differences more precisely where FastText seems to be the most promising representation.

@article{RING2021102389, abstract = {Malware is a constant threat and is continuously evolving. Security systems try to keep up with the constant change. One challenge that arises is the large amount of logs generated on an operating system and the need to clarify which information contributes to the detection of possible malware. This work aims at the detection of malware using neural networks based on Windows audit log events. Neural networks can only process continuous data, but Windows audit logs are sequential and textual data. To address these challenges, we extract features out of the audit log events and use LSTMs to capture sequential effects. We create different subsets of features and analyze the effects of additional information. Features describe for example the action-type of windows audit log events, process names or target files that are accessed. Textual features are represented either as one-hot encoding or embedding representation, for which we compare three different approaches for representation learning. Effects of different feature subsets and representations are evaluated on a publicly available data set. Results indicate that using additional information improves the performance of the LSTM-model. While different representations lead to similar classification results, analysis of the latent space shows differences more precisely where FastText seems to be the most promising representation.}, author = {Ring, Markus and Schlör, Daniel and Wunderlich, Sarah and Landes, Dieter and Hotho, Andreas}, journal = {Computers & Security}, keywords = {LSTM}, pages = 102389, title = {Malware detection on windows audit logs using LSTMs}, volume = 109, year = 2021 }

2020[ to top ]

Schl{ö}r, D., Zehe, A., Kobs, K., Veseli, B., Westermeier, F., Br{ü}bach, L., Roth, D., Latoschik, M.E., and Hotho, A. (2020) “Improving Sentiment Analysis with Biofeedback Data”, in Proceedings of LREC2020 Workshop ``People in Language, Vision and the mind’’ (ONION2020), Marseille, France: European Language Resources Association (ELRA), 28–33, available: https://www.aclweb.org/anthology/2020.onion-1.5.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories. For computers, however, emotion recognition is a complex problem: Thoughts and feelings are the roots of many behavioural responses and they are deeply entangled with neurophysiological changes within humans. As such, emotions are very subjective, often are expressed in a subtle manner, and are highly depending on context. For example, machine learning approaches for text-based sentiment analysis often rely on incorporating sentiment lexicons or language models to capture the contextual meaning. This paper explores if and how we further can enhance sentiment analysis using biofeedback of humans which are experiencing emotions while reading texts. Specifically, we record the heart rate and brain waves of readers that are presented with short texts which have been annotated with the emotions they induce. We use these physiological signals to improve the performance of a lexicon-based sentiment classifier. We find that the combination of several biosignals can improve the ability of a text-based classifier to detect the presence of a sentiment in a text on a per-sentence level.

@inproceedings{schlor-etal-2020-improving, abstract = {Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories. For computers, however, emotion recognition is a complex problem: Thoughts and feelings are the roots of many behavioural responses and they are deeply entangled with neurophysiological changes within humans. As such, emotions are very subjective, often are expressed in a subtle manner, and are highly depending on context. For example, machine learning approaches for text-based sentiment analysis often rely on incorporating sentiment lexicons or language models to capture the contextual meaning. This paper explores if and how we further can enhance sentiment analysis using biofeedback of humans which are experiencing emotions while reading texts. Specifically, we record the heart rate and brain waves of readers that are presented with short texts which have been annotated with the emotions they induce. We use these physiological signals to improve the performance of a lexicon-based sentiment classifier. We find that the combination of several biosignals can improve the ability of a text-based classifier to detect the presence of a sentiment in a text on a per-sentence level.}, address = {Marseille, France}, author = {Schl{\"o}r, Daniel and Zehe, Albin and Kobs, Konstantin and Veseli, Blerta and Westermeier, Franziska and Br{\"u}bach, Larissa and Roth, Daniel and Latoschik, Marc Erich and Hotho, Andreas}, booktitle = {Proceedings of LREC2020 Workshop ``People in language, vision and the mind'' (ONION2020)}, keywords = {sentimentanalysis}, month = {05}, pages = {28–33}, publisher = {European Language Resources Association (ELRA)}, title = {Improving Sentiment Analysis with Biofeedback Data}, year = 2020 }
Schlör, D., Ring, M., Krause, A., and Hotho, A. (2020) Financial Fraud Detection With Improved Neural Arithmetic Logic Units.
- [ BibTeX ]
- [ Download ]
@proceedings{schlr2020financial, author = {Schlör, Daniel and Ring, Markus and Krause, Anna and Hotho, Andreas}, keywords = {inalu}, number = 5, title = {Financial Fraud Detection with Improved Neural Arithmetic Logic Units}, volume = {Fifth Workshop on MIning DAta for financial applicationS}, year = 2020 }
Schlör, D., Ring, M., and Hotho, A. (2020) “iNALU: Improved Neural Arithmetic Logic Unit”, Frontiers in Artificial Intelligence, 3, 71, available: https://doi.org/10.3389/frai.2020.00071.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
Neural networks have to capture mathematical relationships in order to learn various tasks. They approximate these relations implicitly and therefore often do not generalize well. The recently proposed Neural Arithmetic Logic Unit (NALU) is a novel neural architecture which is able to explicitly represent the mathematical relationships by the units of the network to learn operations such as summation, subtraction or multiplication. Although NALUs have been shown to perform well on various downstream tasks, an in-depth analysis reveals practical shortcomings by design, such as the inability to multiply or divide negative input values or training stability issues for deeper networks. We address these issues and propose an improved model architecture. We evaluate our model empirically in various settings from learning basic arithmetic operations to more complex functions. Our experiments indicate that our model solves stability issues and outperforms the original NALU model in means of arithmetic precision and convergence.

@article{10.3389/frai.2020.00071, abstract = {Neural networks have to capture mathematical relationships in order to learn various tasks. They approximate these relations implicitly and therefore often do not generalize well. The recently proposed Neural Arithmetic Logic Unit (NALU) is a novel neural architecture which is able to explicitly represent the mathematical relationships by the units of the network to learn operations such as summation, subtraction or multiplication. Although NALUs have been shown to perform well on various downstream tasks, an in-depth analysis reveals practical shortcomings by design, such as the inability to multiply or divide negative input values or training stability issues for deeper networks. We address these issues and propose an improved model architecture. We evaluate our model empirically in various settings from learning basic arithmetic operations to more complex functions. Our experiments indicate that our model solves stability issues and outperforms the original NALU model in means of arithmetic precision and convergence.}, author = {Schlör, Daniel and Ring, Markus and Hotho, Andreas}, journal = {Frontiers in Artificial Intelligence}, keywords = {inalu}, pages = 71, title = {iNALU: Improved Neural Arithmetic Logic Unit}, volume = 3, year = 2020 }
Tritscher, J., Ring, M., Schlör, D., Hettinger, L., and Hotho, A. (2020) “Evaluation of Post-hoc XAI Approaches Through Synthetic Tabular Data.”, in Helic, D., Leitner, G., Stettinger, M., Felfernig, A. and Ras, Z.W., eds., ISMIS, Lecture Notes in Computer Science, Springer, 422–430, available: http://dblp.uni-trier.de/db/conf/ismis/ismis2020.html#TritscherRSHH20.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@inproceedings{conf/ismis/TritscherRSHH20, author = {Tritscher, Julian and Ring, Markus and Schlör, Daniel and Hettinger, Lena and Hotho, Andreas}, booktitle = {ISMIS}, crossref = {conf/ismis/2020}, editor = {Helic, Denis and Leitner, Gerhard and Stettinger, Martin and Felfernig, Alexander and Ras, Zbigniew W.}, keywords = {xai}, pages = {422-430}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Evaluation of Post-hoc XAI Approaches Through Synthetic Tabular Data.}, volume = 12117, year = 2020 }

2019[ to top ]

Schl{ö}r, D., Sch{ö}ch, C., and Hotho, A. (2019) “Classification of text-types in german novels”, in Digital Humanities 2019: Conference Abstracts, available: https://doi.org/https://doi.org/10.34894/OMLKRN.
- [ BibTeX ]
- [ Download ]
@inproceedings{schlor2019classification, author = {Schl{\"o}r, D and Sch{\"o}ch, C and Hotho, A}, booktitle = {Digital Humanities 2019: Conference Abstracts}, keywords = {myown}, title = {Classification of text-types in german novels}, year = 2019 }
Ring, M., Schlör, D., Landes, D., and Hotho, A. (2019) “Flow-based network traffic generation using Generative Adversarial Networks.”, Comput. Secur., 82, 156–172, available: http://dblp.uni-trier.de/db/journals/compsec/compsec82.html#RingSLH19.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@article{journals/compsec/RingSLH19, author = {Ring, Markus and Schlör, Daniel and Landes, Dieter and Hotho, Andreas}, journal = {Comput. Secur.}, keywords = {traffic}, pages = {156-172}, title = {Flow-based network traffic generation using Generative Adversarial Networks.}, volume = 82, year = 2019 }

2018[ to top ]

Schöch, C., Schlör, D., Zehe, A., Gebhard, H., Becker, M., and Hotho, A. (2018) “Burrows’ Zeta: Exploring and Evaluating Variants and Parameters”, in DH, 274–277, available: http://dblp.uni-trier.de/db/conf/dihu/dh2018.html#SchochSZG0H18.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@inproceedings{schoech2018zeta, author = {Schöch, Christof and Schlör, Daniel and Zehe, Albin and Gebhard, Henning and Becker, Martin and Hotho, Andreas}, booktitle = {DH}, keywords = {zeta}, pages = {274-277}, title = {Burrows’ Zeta: Exploring and Evaluating Variants and Parameters}, year = 2018 }
Zehe, A., Schlör, D., Henny-Krahmer, U., Becker, M., and Hotho, A. (2018) “A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels”, in DH, ADHO.
- [ BibTeX ]
- [ Download ]
@inproceedings{zehe2018whitebox, author = {Zehe, Albin and Schlör, Daniel and Henny-Krahmer, Ulrike and Becker, Martin and Hotho, Andreas}, booktitle = {DH}, keywords = {cligs}, organization = {ADHO}, title = {A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels}, year = 2018 }

2017[ to top ]

Tello, J.C., Schlör, D., Henny-Krahmer, U., and Schöch, C. (2017) “Neutralising the Authorial Signal in Delta by Penalization: Stylometric Clustering of Genre in Spanish Novels.”, in Lewis, R., Raynor, C., Forest, D., Sinatra, M. and Sinclair, S., eds., DH, Alliance of Digital Humanities Organizations (ADHO), available: http://dblp.uni-trier.de/db/conf/dihu/dh2017.html#TelloSHS17.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@inproceedings{conf/dihu/TelloSHS17, author = {Tello, José Calvo and Schlör, Daniel and Henny-Krahmer, Ulrike and Schöch, Christof}, booktitle = {DH}, crossref = {conf/dihu/2017}, editor = {Lewis, Rhian and Raynor, Cecily and Forest, Dominic and Sinatra, Michael and Sinclair, Stéfan}, keywords = {stylometry}, publisher = {Alliance of Digital Humanities Organizations (ADHO)}, title = {Neutralising the Authorial Signal in Delta by Penalization: Stylometric Clustering of Genre in Spanish Novels.}, year = 2017 }

2016[ to top ]

Niebler, T., Schlör, D., Becker, M., and Hotho, A. (2016) “Extracting Semantics from Unconstrained Navigation on Wikipedia”, KI -- Künstliche Intelligenz, 30(2), 163–168.
- [ Abstract ]
- [ BibTeX ]
Semantic relatedness between words has been successfully extracted from navigation on Wikipedia pages. However, the navigational data used in the corresponding works are sparse and expected to be biased since they have been collected in the context of games. In this paper, we raise this limitation and explore if semantic relatedness can also be extracted from unconstrained navigation. To this end, we first highlight structural differences between unconstrained navigation and game data. Then, we adapt a state of the art approach to extract semantic relatedness on Wikipedia paths. We apply this approach to transitions derived from two unconstrained navigation datasets as well as transitions from WikiGame and compare the results based on two common gold standards. We confirm expected structural differences when comparing unconstrained navigation with the paths collected by WikiGame. In line with this result, the mentioned state of the art approach for semantic extraction on navigation data does not yield good results for unconstrained navigation. Yet, we are able to derive a relatedness measure that performs well on both unconstrained navigation data as well as game data. Overall, we show that unconstrained navigation data on Wikipedia is suited for extracting semantics.

@article{niebler2016extracting, abstract = {Semantic relatedness between words has been successfully extracted from navigation on Wikipedia pages. However, the navigational data used in the corresponding works are sparse and expected to be biased since they have been collected in the context of games. In this paper, we raise this limitation and explore if semantic relatedness can also be extracted from unconstrained navigation. To this end, we first highlight structural differences between unconstrained navigation and game data. Then, we adapt a state of the art approach to extract semantic relatedness on Wikipedia paths. We apply this approach to transitions derived from two unconstrained navigation datasets as well as transitions from WikiGame and compare the results based on two common gold standards. We confirm expected structural differences when comparing unconstrained navigation with the paths collected by WikiGame. In line with this result, the mentioned state of the art approach for semantic extraction on navigation data does not yield good results for unconstrained navigation. Yet, we are able to derive a relatedness measure that performs well on both unconstrained navigation data as well as game data. Overall, we show that unconstrained navigation data on Wikipedia is suited for extracting semantics.}, author = {Niebler, Thomas and Schlör, Daniel and Becker, Martin and Hotho, Andreas}, journal = {KI – Künstliche Intelligenz}, keywords = {unconstrained}, number = 2, pages = {163–168}, publisher = {Springer}, title = {Extracting Semantics from Unconstrained Navigation on Wikipedia}, volume = 30, year = 2016 }
Sch{ö}ch, C., Schl{ö}r, D., Popp, S., Brunner, A., Henny, U., and Tello, J.C. (2016) “Straight Talk! Automatic Recognition of Direct Speech in Nineteenth-Century French Novels.”, in DH, 346–353.
- [ BibTeX ]
- [ Download ]
@inproceedings{schoch2016straight, author = {Sch{\"o}ch, Christof and Schl{\"o}r, Daniel and Popp, Stefanie and Brunner, Annelen and Henny, Ulrike and Tello, Jos{\'e} Calvo}, booktitle = {DH}, keywords = {directspeech}, pages = {346–353}, title = {Straight Talk! Automatic Recognition of Direct Speech in Nineteenth-Century French Novels.}, year = 2016 }