Hubert Baniecki

University of WarsawWarsaw University of TechnologyMI².AI

h.baniecki (at)

I am a 2nd year PhD student in Computer Science at the University of Warsaw advised by Przemyslaw Biecek. In spring 2024, I was as a visiting researcher at LMU Munich hosted by Bernd Bischl and Giuseppe Casalicchio. Prior, I completed a Master’s degree in Data Science at Warsaw University of Technology.

My main research interest is explainable machine learning, with a particular emphasis on the robustness of post-hoc explanations to adversarial attacks. I also care about human-model interaction with applications in medicine, and support the development of several open-source Python & R packages for building predictive models responsibly.

I received the 2022 John M. Chambers Statistical Software Award.

recent news [previous]

2024 Jul I will present a paper Efficient and accurate explanation estimation with distribution compression at the ICML 2024 Workshop on DMLR.
2024 Jun I received the Minister’s (of Science and Higher Education, Poland) scholarship for outstanding young scientists.
2024 May A paper On the robustness of global feature effect explanations is accepted at ECML PKDD 2024.
2024 Apr A paper Performance is not enough: The story told by a Rashomon quartet is accepted for publication in the Journal of Computational and Graphical Statistics.
2024 Apr Two papers on Red teaming are accepted at ICLR 2024 Workshops and CVPR 2024 Workshops .

selected publications [full list]

    1. On the robustness of global feature effect explanations
      H. Baniecki, G. Casalicchio, B. Bischl, P. Biecek
      ECML PKDD 2024
      Theoretical bounds for the robustness of feature effects to data and model perturbations.
    2. Adversarial attacks and defenses in explainable artificial intelligence: A survey
      H. Baniecki, P. Biecek
      Information Fusion, 2024
      Review of adversarial attacks on explanations and how to defend them.
    3. The grammar of interactive explanatory model analysis
      H. Baniecki, D. Parzych, P. Biecek
      Data Mining and Knowledge Discovery, 2023
      Interactive explanation of a model improves the performance of human decision making.
    4. Fooling partial dependence via data poisoning
      H. Baniecki, W. Kretowicz, P. Biecek
      ECML PKDD 2022
      Feature effect explanations can be manipulated in an adversarial manner.
    5. dalex: Responsible machine learning with interactive explainability and fairness in Python
      H. Baniecki, W. Kretowicz, P. Piatyszek, J. Wisniewski, P. Biecek
      Journal of Machine Learning Research, 2021
      2022 John M. Chambers Statistical Software Award