Hubert Baniecki

find me @hbaniecki

I’m an MSc student in Data Science at Warsaw University of Technology; working in the MI² research lab led by Przemysław Biecek.

My research interests include explainable machine learning, responsibility, evaluation and adversarial attacks.

Developing and maintaining open-source Python & R packages used for explainability of predictive models.

news [archive]

2022-Jun new paper	Fooling Partial Dependence via Data Poisoning Accepted for publication at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD’22).
2022-Jun	Admissioned to PhD in Computer Science at the University of Warsaw and got funded by the project ARES: Attack-Resistant Explanations toward Secure and trustworthy AI (426K PLN ).
2022-Mar	Received the Minister’s (of Education and Science, Poland) scholarship for students for significant scientific achievements.
2022-Jan	dalex received the John M. Chambers Statistical Software Award combined with my invited talk at the 2022 Joint Statistical Meetings, Washington DC, USA.
2021-Oct new paper	Manipulating SHAP via Adversarial Data Perturbations (Student Abstract) Accepted for publication at the AAAI Conference on Artificial Intelligence (AAAI’22).

highlights

ECML PKDD BSc

Fooling Partial Dependence via Data Poisoning

H. Baniecki, W. Kretowicz, P. Biecek

In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2022
Note: This paper is the core of our BSc thesis defended at Warsaw University of Technology.

Abstract PDF arXiv Code

Many methods have been developed to understand complex predictive models and high expectations are placed on post-hoc model explainability. It turns out that such explanations are not robust nor trustworthy, and they can be fooled. This paper presents techniques for attacking Partial Dependence (plots, profiles, PDP), which are among the most popular methods of explaining any predictive model trained on tabular data. We showcase that PD can be manipulated in an adversarial manner, which is alarming, especially in financial or medical applications where auditability became a must-have trait supporting black-box models. The fooling is performed via poisoning the data to bend and shift explanations in the desired direction using genetic and gradient algorithms. To the best of our knowledge, this is the first work using a genetic algorithm for attacking explanations, which is highly transferable as it generalizes both ways: in a model-agnostic and an explanation-agnostic manner.
AAAI SA

Manipulating SHAP via Adversarial Data Perturbations (Student Abstract)

H. Baniecki, P. Biecek

In: AAAI Conference on Artificial Intelligence (AAAI), 2022

Abstract HTML Code Poster

We introduce a model-agnostic algorithm for manipulating SHapley Additive exPlanations (SHAP) with perturbation of tabular data. It is evaluated on predictive tasks from healthcare and financial domains to illustrate how crucial is the context of data distribution in interpreting machine learning models. Our method supports checking the stability of the explanations used by various stakeholders apparent in the domain of responsible AI; moreover, the result highlights the explanations' vulnerability that can be exploited by an adversary.
JMLR MLOSS

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

Abstract HTML Code Website

In modern machine learning, we observe the phenomenon of opaqueness debt, which manifests itself by an increased risk of discrimination, lack of reproducibility, and deflated performance due to data drift. An increasing amount of available data and computing power results in the growing complexity of black-box predictive models. To manage these issues, good MLOps practice asks for better validation of model performance and fairness, higher explainability, and continuous monitoring. The necessity for deeper model transparency comes from both scientific and social domains and is also caused by emerging laws and regulations on artificial intelligence. To facilitate the responsible development of machine learning models, we introduce dalex, a Python package which implements a model-agnostic interface for interactive explainability and fairness. It adopts the design crafted through the development of various tools for explainable machine learning; thus, it aims at the unification of existing solutions. This library's source code and documentation are available under open license at https://python.drwhy.ai.