v1v2 (latest)

Interpretation of Neural Networks is Fragile

AAAI Conference on Artificial Intelligence (AAAI), 2017

29 October 2017

Papers citing "Interpretation of Neural Networks is Fragile"

50 / 489 papers shown

Title
Towards the Unification and Robustness of Perturbation and Gradient Based ExplanationsInternational Conference on Machine Learning (ICML), 2021 Sushant Agarwal S. Jabbari Chirag Agarwal Sohini Upadhyay Zhiwei Steven Wu Himabindu Lakkaraju FAtt AAML 271 70 0 21 Feb 2021
The Mind's Eye: Visualizing Class-Agnostic Features of CNNsInternational Conference on Information Photonics (ICIP), 2021 Alexandros Stergiou FAtt 68 4 0 29 Jan 2021
Better sampling in explanation methods can prevent dieselgate-like deception Domen Vreš Marko Robnik-Šikonja AAML 104 11 0 26 Jan 2021
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systemsComputer Vision and Image Understanding (CVIU), 2021 Utku Ozbulak Baptist Vandersmissen A. Jalalvand Ivo Couckuyt Arnout Van Messem W. D. Neve AAML 81 20 0 26 Jan 2021
Show or Suppress? Managing Input Uncertainty in Machine Learning Model ExplanationsArtificial Intelligence (AI), 2021 Danding Wang Wencan Zhang Brian Y. Lim FAtt 93 27 0 23 Jan 2021
How can I choose an explainer? An Application-grounded Evaluation of Post-hoc ExplanationsConference on Fairness, Accountability and Transparency (FAccT), 2021 Sérgio Jesus Catarina Belém Vladimir Balayan João Bento Pedro Saleiro P. Bizarro João Gama 378 129 0 21 Jan 2021
Towards interpreting ML-based automated malware detection models: a survey Yuzhou Lin Xiaolin Chang 271 8 0 15 Jan 2021
Explainability of deep vision-based autonomous driving systems: Review and challengesInternational Journal of Computer Vision (IJCV), 2021 Éloi Zablocki H. Ben-younes P. Pérez Matthieu Cord XAI 420 203 0 13 Jan 2021
Enhanced Regularizers for Attributional RobustnessAAAI Conference on Artificial Intelligence (AAAI), 2020 A. Sarkar Anirban Sarkar V. Balasubramanian 157 17 0 28 Dec 2020
A Survey on Neural Network InterpretabilityIEEE Transactions on Emerging Topics in Computational Intelligence (IEEE TETCI), 2020 Yu Zhang Peter Tiño A. Leonardis Shengcai Liu FaML XAI 462 814 0 28 Dec 2020
To what extent do human explanations of model behavior align with actual model behavior?BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP), 2020 Grusha Prasad Yixin Nie Joey Tianyi Zhou Robin Jia Douwe Kiela Adina Williams 183 28 0 24 Dec 2020
Towards Robust Explanations for Deep Neural NetworksPattern Recognition (Pattern Recognit.), 2020 Ann-Kathrin Dombrowski Christopher J. Anders K. Müller Pan Kessel FAtt 195 66 0 18 Dec 2020
Robustness to Spurious Correlations in Text Classification via Automatically Generated CounterfactualsAAAI Conference on Artificial Intelligence (AAAI), 2020 Zhao Wang A. Culotta CML OOD 170 108 0 18 Dec 2020
Debiased-CAM to mitigate image perturbations with faithful visual explanations of machine learningInternational Conference on Human Factors in Computing Systems (CHI), 2020 Wencan Zhang Mariella Dimiccoli Brian Y. Lim FAtt 315 19 0 10 Dec 2020
Understanding Interpretability by generalized distillation in Supervised Classification Adit Agarwal Dr. K.K. Shukla Arjan Kuijper Anirban Mukhopadhyay FaML FAtt 128 0 0 05 Dec 2020
LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering Weixin Liang Fei Niu Aishwarya N. Reganti Govind Thattai Gokhan Tur 163 19 0 21 Nov 2020
Backdoor Attacks on the DNN Interpretation SystemAAAI Conference on Artificial Intelligence (AAAI), 2020 Shihong Fang A. Choromańska FAtt AAML 196 22 0 21 Nov 2020
One Explanation is Not Enough: Structured Attention Graphs for Image ClassificationNeural Information Processing Systems (NeurIPS), 2020 Vivswan Shitole Li Fuxin Minsuk Kahng Prasad Tadepalli Alan Fern FAtt GNN 281 45 0 13 Nov 2020
Robust and Stable Black Box ExplanationsInternational Conference on Machine Learning (ICML), 2020 Himabindu Lakkaraju Nino Arsov Osbert Bastani AAML FAtt 160 91 0 12 Nov 2020
Debugging Tests for Model Explanations Julius Adebayo M. Muelly Ilaria Liccardi Been Kim FAtt 266 198 0 10 Nov 2020
Benchmarking Deep Learning Interpretability in Time Series PredictionsNeural Information Processing Systems (NeurIPS), 2020 Aya Abdelsalam Ismail Mohamed K. Gunady H. C. Bravo Soheil Feizi XAI AI4TS FAtt 275 203 0 26 Oct 2020
Measuring Association Between Labels and Free-Text RationalesConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 Sarah Wiegreffe Ana Marasović Noah A. Smith 632 194 0 24 Oct 2020
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization Judy Borowski Roland S. Zimmermann Judith Schepers Robert Geirhos Thomas S. A. Wallis Matthias Bethge Wieland Brendel FAtt 209 7 0 23 Oct 2020
Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial RobustnessProceedings of the IEEE (Proc. IEEE), 2020 Guillermo Ortiz-Jiménez Apostolos Modas Seyed-Mohsen Moosavi-Dezfooli P. Frossard AAML 320 50 0 19 Oct 2020
Evaluating Attribution Methods using White-Box LSTMsBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP), 2020 Sophie Hao FAtt XAI 181 8 0 16 Oct 2020
FAR: A General Framework for Attributional Robustness Adam Ivankay Ivan Girardi Chiara Marchiori P. Frossard OOD 220 22 0 14 Oct 2020
Learning Propagation Rules for Attribution Map Generation Yiding Yang Jiayan Qiu Xiuming Zhang Dacheng Tao Xinchao Wang FAtt 140 17 0 14 Oct 2020
Neural Gaussian Mirror for Controlled Feature Selection in Neural Networks Xin Xing Yu Gui Chenguang Dai Jun S. Liu AAML 140 6 0 13 Oct 2020
Gradient-based Analysis of NLP Models is Manipulable Junlin Wang Jens Tuyls Eric Wallace Sameer Singh AAML FAtt 164 62 0 12 Oct 2020
Explaining Clinical Decision Support Systems in Medical Imaging using Cycle-Consistent Activation MaximizationNeurocomputing (Neurocomputing), 2020 Alexander Katzmann O. Taubmann Stephen Ahmad Alexander Muhlberg M. Sühling H. Groß MedIm 135 26 0 09 Oct 2020
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects Amir-Hossein Karimi Gilles Barthe Bernhard Schölkopf Isabel Valera FaML 327 182 0 08 Oct 2020
Information-Theoretic Visual Explanation for Black-Box Classifiers Jihun Yi Eunji Kim Siwon Kim Sungroh Yoon FAtt 168 6 0 23 Sep 2020
What Do You See? Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural BackdoorsKnowledge Discovery and Data Mining (KDD), 2020 Yi-Shan Lin Wen-Chuan Lee Z. Berkay Celik XAI 191 105 0 22 Sep 2020
Reconstructing Actions To Explain Deep Reinforcement Learning Xuan Chen Zifan Wang Yucai Fan Bonan Jin Piotr (Peter) Mardziel Carlee Joe-Wong Anupam Datta FAtt 239 2 0 17 Sep 2020
Evolutionary Selective Imitation: Interpretable Agents by Imitation Learning Without a Demonstrator Roy Eliya J. Herrmann 107 2 0 17 Sep 2020
Are Interpretations Fairly Evaluated? A Definition Driven Pipeline for Post-Hoc Interpretability Ninghao Liu Yunsong Meng Helen Zhou Tie Wang Bo Long XAI FAtt 167 7 0 16 Sep 2020
How Good is your Explanation? Algorithmic Stability Measures to Assess the Quality of Explanations for Deep Neural NetworksIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2020 Thomas Fel David Vigouroux Rémi Cadène Thomas Serre XAI FAtt 365 34 0 07 Sep 2020
Model extraction from counterfactual explanations Ulrich Aïvodji Alexandre Bolot Sébastien Gambs MIACV MLAU 189 58 0 03 Sep 2020
Relevance Attack on Detectors Sizhe Chen Fan He Xiaolin Huang Kun Zhang AAML 204 18 0 16 Aug 2020
Can We Trust Your Explanations? Sanity Checks for Interpreters in Android Malware Analysis Ming Fan Wenying Wei Xiaofei Xie Yang Liu X. Guan Ting Liu FAtt AAML 284 43 0 13 Aug 2020
Reliable Post hoc Explanations: Modeling Uncertainty in ExplainabilityNeural Information Processing Systems (NeurIPS), 2020 Dylan Slack Sophie Hilgard Sameer Singh Himabindu Lakkaraju FAtt 523 200 0 11 Aug 2020
Fairwashing Explanations with Off-Manifold Detergent Christopher J. Anders Plamen Pasliev Ann-Kathrin Dombrowski K. Müller Pan Kessel FAtt FaML 140 103 0 20 Jul 2020
A simple defense against adversarial attacks on heatmap explanations Laura Rieger Lars Kai Hansen FAtt AAML 208 39 0 13 Jul 2020
Regional Image Perturbation Reduces $L_p$ Norms of Adversarial Examples While Maintaining Model-to-model Transferability Utku Ozbulak Jonathan Peck W. D. Neve Bart Goossens Yvan Saeys Arnout Van Messem AAML 124 2 0 07 Jul 2020
Unifying Model Explainability and Robustness via Machine-Checkable Concepts Vedant Nanda Till Speicher John P. Dickerson Krishna P. Gummadi Muhammad Bilal Zafar AAML 163 4 0 01 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 213 72 0 26 Jun 2020
Influence Functions in Deep Learning Are Fragile S. Basu Phillip E. Pope Soheil Feizi TDI 385 281 0 25 Jun 2020
Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey Arun Das P. Rad XAI 386 696 0 16 Jun 2020
On Saliency Maps and Adversarial Robustness Puneet Mangla Vedant Singh V. Balasubramanian AAML 170 18 0 14 Jun 2020
Explainable Artificial Intelligence: a Systematic Review Giulia Vilone Luca Longo XAI 551 300 0 29 May 2020