Interpretation of Neural Networks is Fragile

29 October 2017

Papers citing "Interpretation of Neural Networks is Fragile"

50 / 467 papers shown

Title
Evaluation of Neural Networks Defenses and Attacks using NDCG and Reciprocal Rank Metrics Haya Brama L. Dery Tal Grinshpoun AAML 19 7 0 10 Jan 2022
Topological Representations of Local Explanations Peter Xenopoulos G. Chan Harish Doraiswamy L. G. Nonato Brian Barr Claudio Silva FAtt 28 4 0 06 Jan 2022
GPEX, A Framework For Interpreting Artificial Neural Networks Amir Akbarnejad G. Bigras Nilanjan Ray 47 4 0 18 Dec 2021
Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning Wenjie Shi Gao Huang Shiji Song Cheng Wu 31 9 0 06 Dec 2021
Multi-objective Explanations of GNN Predictions Yifei Liu Chao Chen Yazheng Liu Xi Zhang Sihong Xie 18 13 0 29 Nov 2021
Improving Deep Learning Interpretability by Saliency Guided Training Aya Abdelsalam Ismail H. C. Bravo S. Feizi FAtt 20 80 0 29 Nov 2021
Selective Ensembles for Consistent Predictions Emily Black Klas Leino Matt Fredrikson 20 21 0 16 Nov 2021
Statistical Perspectives on Reliability of Artificial Intelligence Systems Yili Hong J. Lian Li Xu Jie Min Yueyao Wang Laura J. Freeman Xinwei Deng 30 30 0 09 Nov 2021
Defense Against Explanation Manipulation Ruixiang Tang Ninghao Liu Fan Yang Na Zou Xia Hu AAML 44 11 0 08 Nov 2021
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis Thomas Fel Rémi Cadène Mathieu Chalvidal Matthieu Cord David Vigouroux Thomas Serre MLAU FAtt AAML 117 58 0 07 Nov 2021
Callee: Recovering Call Graphs for Binaries with Transfer and Contrastive Learning Wenyu Zhu Zhiyao Feng Zihan Zhang Jian-jun Chen Zhijian Ou Min Yang Chao Zhang AAML 14 8 0 02 Nov 2021
Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods Zohaib Salahuddin Henry C. Woodruff A. Chatterjee Philippe Lambin 24 303 0 01 Nov 2021
A Survey on the Robustness of Feature Importance and Counterfactual Explanations Saumitra Mishra Sanghamitra Dutta Jason Long Daniele Magazzeni AAML 14 58 0 30 Oct 2021
On the explainability of hospitalization prediction on a large COVID-19 patient dataset Ivan Girardi P. Vagenas Dario Arcos-Díaz Lydia Bessaï Alexandra Büsser ... R. Furlan Mauro Gatti Andrea Giovannini Ellen Hoeven Chiara Marchiori FAtt 24 3 0 28 Oct 2021
Provably Robust Model-Centric Explanations for Critical Decision-Making Cecilia G. Morales Nick Gisolfi R. Edman J. K. Miller A. Dubrawski 16 0 0 26 Oct 2021
Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learning Bang Xiang Yong Alexandra Brintrup 21 6 0 19 Oct 2021
The Irrationality of Neural Rationale Models Yiming Zheng Serena Booth J. Shah Yilun Zhou 35 16 0 14 Oct 2021
Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools Davis Brown Henry Kvinge AAML 45 7 0 14 Oct 2021
CloudPred: Predicting Patient Phenotypes From Single-cell RNA-seq B. He M. Thomson Meena Subramaniam Richard K. Perez Chun Jimmie Ye J. Zou 6 15 0 13 Oct 2021
Implicit Bias of Linear Equivariant Networks Hannah Lawrence Kristian Georgiev A. Dienes B. Kiani AI4CE 40 14 0 12 Oct 2021
Consistent Counterfactuals for Deep Models Emily Black Zifan Wang Matt Fredrikson Anupam Datta BDL OffRL OOD 55 43 0 06 Oct 2021
NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks F. Siciliano Maria Sofia Bucarelli Gabriele Tolomei Fabrizio Silvestri GNN AI4CE 22 6 0 05 Oct 2021
AdjointBackMapV2: Precise Reconstruction of Arbitrary CNN Unit's Activation via Adjoint Operators Qing Wan Siu Wun Cheung Yoonsuck Choe 29 0 0 04 Oct 2021
Trustworthy AI: From Principles to Practices Bo-wen Li Peng Qi Bo Liu Shuai Di Jingen Liu Jiquan Pei Jinfeng Yi Bowen Zhou 119 356 0 04 Oct 2021
Adversarial Regression with Doubly Non-negative Weighting Matrices Tam Le Truyen V. Nguyen M. Yamada Jose H. Blanchet Viet Anh Nguyen 27 5 0 30 Sep 2021
Deep neural networks with controlled variable selection for the identification of putative causal genetic variants P. H. Kassani Fred Lu Yann Le Guen Zihuai He 18 12 0 29 Sep 2021
Discriminative Attribution from Counterfactuals N. Eckstein A. S. Bates G. Jefferis Jan Funke FAtt CML 27 1 0 28 Sep 2021
DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications Dongqi Han Zhiliang Wang Wenqi Chen Ying Zhong Su Wang Han Zhang Jiahai Yang Xingang Shi Xia Yin AAML 24 76 0 23 Sep 2021
Ranking Feature-Block Importance in Artificial Multiblock Neural Networks Anna Jenul Stefan Schrunner B. Huynh Runar Helin C. Futsaether K. H. Liland O. Tomic FAtt 24 1 0 21 Sep 2021
FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imaging Karim Lekadira Richard Osuala C. Gallin Noussair Lazrak Kaisar Kushibar ... Nickolas Papanikolaou Zohaib Salahuddin Henry C. Woodruff Philippe Lambin L. Martí-Bonmatí AI4TS 71 56 0 20 Sep 2021
Self-learn to Explain Siamese Networks Robustly Chao Chen Yifan Shen Guixiang Ma Xiangnan Kong S. Rangarajan Xi Zhang Sihong Xie 46 5 0 15 Sep 2021
Rationales for Sequential Predictions Keyon Vafa Yuntian Deng David M. Blei Alexander M. Rush 12 33 0 14 Sep 2021
Logic Traps in Evaluating Attribution Scores Yiming Ju Yuanzhe Zhang Zhao Yang Zhongtao Jiang Kang Liu Jun Zhao XAI FAtt 30 18 0 12 Sep 2021
EG-Booster: Explanation-Guided Booster of ML Evasion Attacks Abderrahmen Amich Birhanu Eshete AAML 11 8 0 31 Aug 2021
Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience G. Chrysostomou Nikolaos Aletras 32 16 0 31 Aug 2021
Finding Representative Interpretations on Convolutional Neural Networks P. C. Lam Lingyang Chu Maxim Torgonskiy J. Pei Yong Zhang Lanjun Wang FAtt SSL HAI 27 6 0 13 Aug 2021
Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks Zitao Chen Pritam Dash Karthik Pattabiraman AAML 24 18 0 11 Aug 2021
Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing Sanchit Sinha Hanjie Chen Arshdeep Sekhon Yangfeng Ji Yanjun Qi AAML FAtt 28 42 0 11 Aug 2021
Harnessing value from data science in business: ensuring explainability and fairness of solutions Krzysztof Chomiak Michal Miktus 13 0 0 10 Aug 2021
Explainable AI and susceptibility to adversarial attacks: a case study in classification of breast ultrasound images Hamza Rasaee H. Rivaz AAML 18 18 0 09 Aug 2021
Jointly Attacking Graph Neural Network and its Explanations Wenqi Fan Wei Jin Xiaorui Liu Han Xu Xianfeng Tang Suhang Wang Qing Li Jiliang Tang Jianping Wang Charu C. Aggarwal AAML 42 28 0 07 Aug 2021
Resisting Out-of-Distribution Data Problem in Perturbation of XAI Luyu Qiu Yi Yang Caleb Chen Cao Jing Liu Yueyuan Zheng H. Ngai J. H. Hsiao Lei Chen 9 18 0 27 Jul 2021
Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks Ian E. Nielsen Dimah Dera Ghulam Rasool N. Bouaynaya R. Ramachandran FAtt 20 79 0 23 Jul 2021
Trustworthy AI: A Computational Perspective Haochen Liu Yiqi Wang Wenqi Fan Xiaorui Liu Yaxin Li Shaili Jain Yunhao Liu Anil K. Jain Jiliang Tang FaML 104 196 0 12 Jul 2021
Robust Counterfactual Explanations on Graph Neural Networks Mohit Bajaj Lingyang Chu Zihui Xue J. Pei Lanjun Wang P. C. Lam Yong Zhang OOD 43 96 0 08 Jul 2021
When and How to Fool Explainable Models (and Humans) with Adversarial Examples Jon Vadillo Roberto Santana Jose A. Lozano SILM AAML 36 12 0 05 Jul 2021
Certifiably Robust Interpretation via Renyi Differential Privacy Ao Liu Xiaoyu Chen Sijia Liu Lirong Xia Chuang Gan AAML 19 11 0 04 Jul 2021
Explanation-Guided Diagnosis of Machine Learning Evasion Attacks Abderrahmen Amich Birhanu Eshete AAML 17 10 0 30 Jun 2021
On Locality of Local Explanation Models Sahra Ghalebikesabi Lucile Ter-Minassian Karla Diaz-Ordaz Chris Holmes FedML FAtt 26 39 0 24 Jun 2021
Guided Integrated Gradients: An Adaptive Path Method for Removing Noise A. Kapishnikov Subhashini Venugopalan Besim Avci Benjamin D. Wedin Michael Terry Tolga Bolukbasi 30 90 0 17 Jun 2021