Mardziel, Piotr

5 publications

NeurIPS 2021 Influence Patterns for Explaining Information Flow in BERT Kaiji Lu, Zifan Wang, Piotr Mardziel, Anupam Datta

AAAI 2020 An Information-Theoretic Quantification of Discrimination with Exempt Features Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover

CVPRW 2020 Interpreting Interpretations: Organizing Attribution Methods by Criteria Zifan Wang, Piotr Mardziel, Anupam Datta, Matt Fredrikson

CVPRW 2020 Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel, Xia Hu

NeurIPS 2020 Smoothed Geometry for Robust Attribution Zifan Wang, Haofan Wang, Shakul Ramkumar, Piotr Mardziel, Matt Fredrikson, Anupam Datta