Maximilian Wolf, M.Sc.

Maximilian Wolf

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

Email: maximilian.wolf <at> uni-wuerzburg.de maximilian.wolf <at> hs-coburg.de

Research Interests

I joined the DMIR group 2022 for my cooperative doctorates PhD studies (Würzburg & Coburg) after receiving my master's degree in Computer Science at the university of applied sciences and arts Coburg in 2021.
In the Genesis project at Coburg, we are working on the generation of cybersecurity benchmark datasets.
I am currently working on applying e.g generative models on the creation of synthetic benchmark datasets.

Artificial Intelligence - Machine Learning - Synthetic Data Generation

Selected Publications

This is a list of selected publications I have co-authored.

A complete list can be found here.

Publication List

2023[ to top ]

Evaluating feature relevance XAI in network intrusion detection. Tritscher, Julian; Wolf, Maximilian; Hotho, Andreas; Schlör, Daniel. In The World Conference on eXplainable Artificial Intelligence (xAI 2023) - to appear. 2023.
- [ 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 = {myown}, title = {Evaluating feature relevance XAI in network intrusion detection}, year = 2023 }

2020[ to top ]

Impact of Generative Adversarial Networks on NetFlow-Based Traffic Classification. Wolf, Maximilian; Ring, Markus; Landes, Dieter. In CISIS, Vol. 1267 of Advances in Intelligent Systems and Computing, Álvaro Herrero, C. Cambra, D. Urda, J. Sedano, H. Quintián, E. Corchado (eds.), pp. 393–404. Springer, 2020.
- [ BibTeX ]
- [ URL ]
@inproceedings{conf/cisis-spain/WolfRL20, author = {Wolf, Maximilian and Ring, Markus and Landes, Dieter}, booktitle = {CISIS}, crossref = {conf/cisis-spain/2020}, editor = {Herrero, Álvaro and Cambra, Carlos and Urda, Daniel and Sedano, Javier and Quintián, Héctor and Corchado, Emilio}, keywords = {myown}, pages = {393-404}, publisher = {Springer}, series = {Advances in Intelligent Systems and Computing}, title = {Impact of Generative Adversarial Networks on NetFlow-Based Traffic Classification.}, volume = 1267, year = 2020 }

2018[ to top ]

Effect of Explicit Emotional Adaptation on Prosocial Behavior of Humans towards Robots depends on Prior Robot Experience. Kühnlenz, Barbara; Kühnlenz, Kolja; Busse, Fabian; Fortsch, Pascal; Wolf, Maximilian. In RO-MAN, pp. 275–281. IEEE, 2018.
- [ BibTeX ]
- [ URL ]
@inproceedings{conf/ro-man/KuhnlenzKBFW18, author = {Kühnlenz, Barbara and Kühnlenz, Kolja and Busse, Fabian and Fortsch, Pascal and Wolf, Maximilian}, booktitle = {RO-MAN}, crossref = {conf/ro-man/2018}, keywords = {myown}, pages = {275-281}, publisher = {IEEE}, title = {Effect of Explicit Emotional Adaptation on Prosocial Behavior of Humans towards Robots depends on Prior Robot Experience.}, year = 2018 }

Maximilian Wolf

Research Interests

Selected Publications

Publication List

Hinweis zum Datenschutz

Hinweis zum Datenschutz

Bildnachweise