Proper Network Interpretability Helps Adversarial Robustness in Classification

26 June 2020

Papers citing "Proper Network Interpretability Helps Adversarial Robustness in Classification"

36 / 36 papers shown

Title
Impact of Adversarial Attacks on Deep Learning Model Explainability Gazi Nazia Nur Mohammad Ahnaf Sadat AAML FAtt 77 0 0 15 Dec 2024
$Certified $\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions$ Certified $\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions Fan Wang Adams Wai-Kin Kong 40 1 0 10 May 2024
PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis Dipkamal Bhusal Md Tanvirul Alam M. K. Veerabhadran Michael Clifford Sara Rampazzi Nidhi Rastogi AAML 36 1 0 12 Apr 2024
Learning the irreversible progression trajectory of Alzheimer's disease Yipei Wang Bing He S. Risacher A. Saykin Jingwen Yan Xiaoqian Wang 38 0 0 10 Mar 2024
Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape Tiejin Chen Wenwang Huang Linsey Pang Dongsheng Luo Hua Wei OOD 41 0 0 09 Mar 2024
Gradient weighting for speaker verification in extremely low Signal-to-Noise Ratio Yi Ma Kong Aik Lee Ville Hautamaki Meng Ge Haizhou Li 31 0 0 05 Jan 2024
Stability Guarantees for Feature Attributions with Multiplicative Smoothing Anton Xue Rajeev Alur Eric Wong 36 5 0 12 Jul 2023
Adversarial attacks and defenses in explainable artificial intelligence: A survey Hubert Baniecki P. Biecek AAML 42 63 0 06 Jun 2023
Improve Video Representation with Temporal Adversarial Augmentation Jinhao Duan Quanfu Fan Hao-Ran Cheng Xiaoshuang Shi Kaidi Xu AAML AI4TS ViT 23 2 0 28 Apr 2023
A Practical Upper Bound for the Worst-Case Attribution Deviations Fan Wang A. Kong AAML 44 4 0 01 Mar 2023
Provable Robust Saliency-based Explanations Chao Chen Chenghua Guo Guixiang Ma Ming Zeng Xi Zhang Sihong Xie AAML FAtt 27 0 0 28 Dec 2022
Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning Yuyang Gao Siyi Gu Junji Jiang S. Hong Dazhou Yu Liang Zhao 24 39 0 07 Dec 2022
Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning Eldor Abdukhamidov Mohammed Abuhamad Simon S. Woo Eric Chan-Tin Tamer Abuhmed AAML 25 9 0 29 Nov 2022
On the Robustness of Explanations of Deep Neural Network Models: A Survey Amlan Jyoti Karthik Balaji Ganesh Manoj Gayala Nandita Lakshmi Tunuguntla Sandesh Kamath V. Balasubramanian XAI FAtt AAML 32 4 0 09 Nov 2022
Visual Prompting for Adversarial Robustness Aochuan Chen P. Lorenz Yuguang Yao Pin-Yu Chen Sijia Liu VLM VPVLM 25 32 0 12 Oct 2022
PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack Junxuan Huang Yatong An Lu Cheng Bai Chen Junsong Yuan Chunming Qiao 3DPC 27 1 0 14 Sep 2022
Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification System Xin Li Yao Qiang Chengyin Li Sijia Liu D. Zhu OOD MedIm 29 4 0 09 Sep 2022
Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks Tilman Raukur A. Ho Stephen Casper Dylan Hadfield-Menell AAML AI4CE 20 124 0 27 Jul 2022
Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning Tianlong Chen Sijia Liu Shiyu Chang Lisa Amini Zhangyang Wang CLL 21 4 0 15 Jun 2022
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective M. Serrurier Franck Mamalet Thomas Fel Louis Bethune Thibaut Boissin AAML FAtt 26 4 0 14 Jun 2022
Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection Fan Wang A. Kong 61 10 0 15 May 2022
Reverse Engineering of Imperceptible Adversarial Image Perturbations Yifan Gong Yuguang Yao Yize Li Yimeng Zhang Xiaoming Liu X. Lin Sijia Liu AAML 39 20 0 26 Mar 2022
Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation Hanjie Chen Yangfeng Ji OOD AAML VLM 24 21 0 23 Mar 2022
Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis Thomas Fel Mélanie Ducoffe David Vigouroux Rémi Cadène Mikael Capelle C. Nicodeme Thomas Serre AAML 23 41 0 15 Feb 2022
Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment Yuyang Gao Tong Sun Liang Zhao Sungsoo Ray Hong HAI 21 37 0 06 Feb 2022
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI Meike Nauta Jan Trienes Shreyasi Pathak Elisa Nguyen Michelle Peters Yasmin Schmitt Jorg Schlotterer M. V. Keulen C. Seifert ELM XAI 26 395 0 20 Jan 2022
Interpretability Aware Model Training to Improve Robustness against Out-of-Distribution Magnetic Resonance Images in Alzheimer's Disease Classification Merel Kuijs C. Jutzeler Bastian Alexander Rieck Sarah C. Brüningk OOD 13 1 0 15 Nov 2021
Self-Interpretable Model with TransformationEquivariant Interpretation Yipei Wang Xiaoqian Wang 29 23 0 09 Nov 2021
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning? Lijie Fan Sijia Liu Pin-Yu Chen Gaoyuan Zhang Chuang Gan AAML VLM 8 118 0 01 Nov 2021
DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networks Yixiang Wang Jiqiang Liu Xiaolin Chang Jianhua Wang Ricardo J. Rodríguez AAML 17 28 0 14 Oct 2021
When and How to Fool Explainable Models (and Humans) with Adversarial Examples Jon Vadillo Roberto Santana Jose A. Lozano SILM AAML 33 11 0 05 Jul 2021
The Definitions of Interpretability and Learning of Interpretable Models Weishen Pan Changshui Zhang FaML XAI 6 3 0 29 May 2021
Fooling Partial Dependence via Data Poisoning Hubert Baniecki Wojciech Kretowicz P. Biecek AAML 21 23 0 26 May 2021
A Unified Game-Theoretic Interpretation of Adversarial Robustness Jie Ren Die Zhang Yisen Wang Lu Chen Zhanpeng Zhou ... Xu Cheng Xin Eric Wang Meng Zhou Jie Shi Quanshi Zhang AAML 66 22 0 12 Mar 2021
Quantifying the Preferential Direction of the Model Gradient in Adversarial Training With Projected Gradient Descent Ricardo Bigolin Lanfredi Joyce D. Schroeder Tolga Tasdizen 16 11 0 10 Sep 2020
Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding Mathew Monfort Bowen Pan K. Ramakrishnan A. Andonian Barry A. McNamara A. Lascelles Quanfu Fan Dan Gutfreund Rogerio Feris A. Oliva VLM 6 68 0 01 Nov 2019