Explanations can be manipulated and geometry is to blame

19 June 2019

Ann-Kathrin Dombrowski

Maximilian Alber

Christopher J. Anders

Papers citing "Explanations can be manipulated and geometry is to blame"

27 / 77 papers shown

Title
AdjointBackMapV2: Precise Reconstruction of Arbitrary CNN Unit's Activation via Adjoint Operators Qing Wan Siu Wun Cheung Yoonsuck Choe 19 0 0 04 Oct 2021
Toward a Unified Framework for Debugging Concept-based Models A. Bontempelli Fausto Giunchiglia Andrea Passerini Stefano Teso 18 4 0 23 Sep 2021
Self-learn to Explain Siamese Networks Robustly Chao Chen Yifan Shen Guixiang Ma Xiangnan Kong S. Rangarajan Xi Zhang Sihong Xie 38 5 0 15 Sep 2021
Explaining Bayesian Neural Networks Kirill Bykov Marina M.-C. Höhne Adelaida Creosteanu Klaus-Robert Muller Frederick Klauschen Shinichi Nakajima Marius Kloft BDL AAML 28 25 0 23 Aug 2021
Synthetic Benchmarks for Scientific Research in Explainable Machine Learning Yang Liu Sujay Khandagale Colin White W. Neiswanger 31 65 0 23 Jun 2021
Characterizing the risk of fairwashing Ulrich Aivodji Hiromi Arai Sébastien Gambs Satoshi Hara 20 27 0 14 Jun 2021
Towards Rigorous Interpretations: a Formalisation of Feature Attribution Darius Afchar Romain Hennequin Vincent Guigue FAtt 31 20 0 26 Apr 2021
Robust Models Are More Interpretable Because Attributions Look Normal Zifan Wang Matt Fredrikson Anupam Datta OOD FAtt 28 25 0 20 Mar 2021
Do Input Gradients Highlight Discriminative Features? Harshay Shah Prateek Jain Praneeth Netrapalli AAML FAtt 21 57 0 25 Feb 2021
Knowledge Infused Policy Gradients for Adaptive Pandemic Control Kaushik Roy Qi Zhang Manas Gaur A. Sheth 14 12 0 11 Feb 2021
Debiased-CAM to mitigate image perturbations with faithful visual explanations of machine learning Wencan Zhang Mariella Dimiccoli Brian Y. Lim FAtt 18 18 0 10 Dec 2020
Robust and Stable Black Box Explanations Himabindu Lakkaraju Nino Arsov Osbert Bastani AAML FAtt 15 84 0 12 Nov 2020
Visualizing Color-wise Saliency of Black-Box Image Classification Models Yuhki Hatakeyama Hiroki Sakuma Yoshinori Konishi Kohei Suenaga FAtt 14 3 0 06 Oct 2020
Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach Nicholas F Halliwell Freddy Lecue FAtt 17 9 0 29 Sep 2020
Machine Guides, Human Supervises: Interactive Learning with Global Explanations Teodora Popordanoska Mohit Kumar Stefano Teso 6 21 0 21 Sep 2020
Model extraction from counterfactual explanations Ulrich Aivodji Alexandre Bolot Sébastien Gambs MIACV MLAU 27 51 0 03 Sep 2020
A simple defense against adversarial attacks on heatmap explanations Laura Rieger Lars Kai Hansen FAtt AAML 25 37 0 13 Jul 2020
Proper Network Interpretability Helps Adversarial Robustness in Classification Akhilan Boopathy Sijia Liu Gaoyuan Zhang Cynthia Liu Pin-Yu Chen Shiyu Chang Luca Daniel AAML FAtt 16 66 0 26 Jun 2020
How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks Kirill Bykov Marina M.-C. Höhne Klaus-Robert Muller Shinichi Nakajima Marius Kloft UQCV FAtt 19 31 0 16 Jun 2020
Adversarial Infidelity Learning for Model Interpretation Jian Liang Bing Bai Yuren Cao Kun Bai Fei-Yue Wang AAML 41 18 0 09 Jun 2020
Higher-Order Explanations of Graph Neural Networks via Relevant Walks Thomas Schnake Oliver Eberle Jonas Lederer Shinichi Nakajima Kristof T. Schütt Klaus-Robert Muller G. Montavon 26 215 0 05 Jun 2020
Adversarial Attacks and Defenses: An Interpretation Perspective Ninghao Liu Mengnan Du Ruocheng Guo Huan Liu Xia Hu AAML 26 8 0 23 Apr 2020
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications Wojciech Samek G. Montavon Sebastian Lapuschkin Christopher J. Anders K. Müller XAI 41 82 0 17 Mar 2020
Explaining Explanations: Axiomatic Feature Interactions for Deep Networks Joseph D. Janizek Pascal Sturmfels Su-In Lee FAtt 24 143 0 10 Feb 2020
Making deep neural networks right for the right scientific reasons by interacting with their explanations P. Schramowski Wolfgang Stammer Stefano Teso Anna Brugger Xiaoting Shao Hans-Georg Luigs Anne-Katrin Mahlein Kristian Kersting 15 207 0 15 Jan 2020
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods Dylan Slack Sophie Hilgard Emily Jia Sameer Singh Himabindu Lakkaraju FAtt AAML MLAU 14 803 0 06 Nov 2019
Contextual Explanation Networks Maruan Al-Shedivat Kumar Avinava Dubey Eric P. Xing CML 24 82 0 29 May 2017