Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

20 July 2023

Papers citing "Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples"

50 / 53 papers shown

Title
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace Jinluan Yang Anke Tang Didi Zhu Zhengyu Chen Li Shen Leilei Gan MoMe AAML 112 4 0 17 Oct 2024
Threats, Attacks, and Defenses in Machine Unlearning: A Survey Ziyao Liu Huanyi Ye Chen Chen Yongsen Zheng K. Lam AAML MU 63 30 0 20 Mar 2024
MultiDelete for Multimodal Machine Unlearning Jiali Cheng Hadi Amiri MU 77 7 0 18 Nov 2023
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy Zihao Zhu Ruotong Wang Shaokui Wei Li Shen Yanbo Fan Baoyuan Wu AAML SILM 86 10 0 14 Jul 2023
Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features Mingli Zhu Shaokui Wei H. Zha Baoyuan Wu AAML 48 37 0 29 Jun 2023
Reconstructive Neuron Pruning for Backdoor Defense Yige Li X. Lyu Xingjun Ma Nodens Koren Lingjuan Lyu Yue Liu Yugang Jiang AAML 56 44 0 24 May 2023
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization Mingli Zhu Shaokui Wei Li Shen Yanbo Fan Baoyuan Wu AAML 56 53 0 24 Apr 2023
SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency Junfeng Guo Yiming Li Xun Chen Hanqing Guo Lichao Sun Cong Liu AAML MLAU 41 101 0 07 Feb 2023
Imperceptible and Robust Backdoor Attack in 3D Point Cloud Kuofeng Gao Jiawang Bai Baoyuan Wu Mengxi Ya Shutao Xia AAML 3DPC 65 32 0 17 Aug 2022
Data-free Backdoor Removal based on Channel Lipschitzness Runkai Zheng Rong Tang Jianze Li Li Liu AAML 39 105 0 05 Aug 2022
Prior-Guided Adversarial Initialization for Fast Adversarial Training Xiaojun Jia Yong Zhang Xingxing Wei Baoyuan Wu Ke Ma Jue Wang Xiaochun Cao AAML 56 38 0 18 Jul 2022
One-shot Neural Backdoor Erasing via Adversarial Weight Masking Shuwen Chai Jinghui Chen AAML 56 34 0 10 Jul 2022
Removing Batch Normalization Boosts Adversarial Training Haotao Wang Aston Zhang Shuai Zheng Xingjian Shi Mu Li Zhangyang Wang 70 42 0 04 Jul 2022
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning Baoyuan Wu Hongrui Chen Ruotong Wang Zihao Zhu Shaokui Wei Danni Yuan Chaoxiao Shen ELM AAML 55 141 0 25 Jun 2022
BagFlip: A Certified Defense against Data Poisoning Yuhao Zhang Aws Albarghouthi Loris Dántoni AAML 49 24 0 26 May 2022
Towards A Proactive ML Approach for Detecting Backdoor Poison Samples Xiangyu Qi Tinghao Xie Jiachen T. Wang Tong Wu Saeed Mahloujifar Prateek Mittal AAML 32 49 0 26 May 2022
LAS-AT: Adversarial Training with Learnable Attack Strategy Xiaojun Jia Yong Zhang Baoyuan Wu Ke Ma Jue Wang Xiaochun Cao AAML 58 134 0 13 Mar 2022
On the Effectiveness of Adversarial Training against Backdoor Attacks Yinghua Gao Dongxian Wu Jingfeng Zhang Guanhao Gan Shutao Xia Gang Niu Masashi Sugiyama AAML 46 22 0 22 Feb 2022
Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks Bingxu Mu Zhenxing Niu Le Wang Xue Wang Rong Jin G. Hua AAML 32 15 0 13 Feb 2022
Backdoor Defense via Decoupling the Training Process Kunzhe Huang Yiming Li Baoyuan Wu Zhan Qin Kui Ren AAML FedML 47 191 0 05 Feb 2022
AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis Junfeng Guo Ang Li Cong Liu AAML 85 75 0 28 Oct 2021
Adversarial Neuron Pruning Purifies Backdoored Deep Models Dongxian Wu Yisen Wang AAML 77 278 0 27 Oct 2021
Anti-Backdoor Learning: Training Clean Models on Poisoned Data Yige Li X. Lyu Nodens Koren Lingjuan Lyu Yue Liu Xingjun Ma OnRL 59 330 0 22 Oct 2021
Boosting Fast Adversarial Training with Learnable Adversarial Initialization Xiaojun Jia Yong Zhang Baoyuan Wu Jue Wang Xiaochun Cao AAML 66 54 0 11 Oct 2021
Adversarial Unlearning of Backdoors via Implicit Hypergradient Yi Zeng Si-An Chen Won Park Z. Morley Mao Ming Jin R. Jia AAML 104 174 0 07 Oct 2021
Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch Hossein Souri Liam H. Fowl Ramalingam Chellappa Micah Goldblum Tom Goldstein SILM 53 127 0 16 Jun 2021
Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective Yi Zeng Won Park Z. Morley Mao R. Jia AAML 25 210 0 07 Apr 2021
Black-box Detection of Backdoor Attacks with Limited Information and Data Yinpeng Dong Xiao Yang Zhijie Deng Tianyu Pang Zihao Xiao Hang Su Jun Zhu AAML 57 113 0 24 Mar 2021
Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks Yige Li Lingjuan Lyu Nodens Koren X. Lyu Yue Liu Xingjun Ma AAML FedML 63 433 0 15 Jan 2021
Invisible Backdoor Attack with Sample-Specific Triggers Yuezun Li Yiming Li Baoyuan Wu Longkang Li Ran He Siwei Lyu AAML DiffM 74 474 0 07 Dec 2020
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks Jinyuan Jia Yupei Liu Xiaoyu Cao Neil Zhenqiang Gong AAML 59 74 0 07 Dec 2020
Input-Aware Dynamic Backdoor Attack A. Nguyen Anh Tran AAML 58 427 0 16 Oct 2020
Computing Systems for Autonomous Driving: State-of-the-Art and Challenges Liangkai Liu Sidi Lu Ren Zhong Baofu Wu Yongtao Yao Qingyan Zhang Weisong Shi 55 269 0 30 Sep 2020
Perceptual Adversarial Robustness: Defense Against Unseen Threat Models Cassidy Laidlaw Sahil Singla Soheil Feizi AAML OOD 60 185 0 22 Jun 2020
RAB: Provable Robustness Against Backdoor Attacks Maurice Weber Xiaojun Xu Bojan Karlas Ce Zhang Yue Liu AAML 46 161 0 19 Mar 2020
Fast is better than free: Revisiting adversarial training Eric Wong Leslie Rice J. Zico Kolter AAML OOD 122 1,167 0 12 Jan 2020
Efficient Adversarial Training with Transferable Adversarial Examples Haizhong Zheng Ziqi Zhang Juncheng Gu Honglak Lee A. Prakash AAML 47 108 0 27 Dec 2019
Adversarial Training and Robustness for Multiple Perturbations Florian Tramèr Dan Boneh AAML SILM 62 376 0 30 Apr 2019
A new Backdoor Attack in CNNs by training set corruption without label poisoning Mauro Barni Kassem Kallas B. Tondi AAML 103 353 0 12 Feb 2019
Theoretically Principled Trade-off between Robustness and Accuracy Hongyang R. Zhang Yaodong Yu Jiantao Jiao Eric Xing L. Ghaoui Michael I. Jordan 98 2,525 0 24 Jan 2019
Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering Bryant Chen Wilka Carvalho Wenjie Li Heiko Ludwig Benjamin Edwards Chengyao Chen Ziqiang Cao Biplav Srivastava AAML 75 786 0 09 Nov 2018
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks Kang Liu Brendan Dolan-Gavitt S. Garg AAML 61 1,028 0 30 May 2018
Robustness May Be at Odds with Accuracy Dimitris Tsipras Shibani Santurkar Logan Engstrom Alexander Turner Aleksander Madry AAML 88 1,772 0 30 May 2018
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks Ali Shafahi Wenjie Huang Mahyar Najibi Octavian Suciu Christoph Studer Tudor Dumitras Tom Goldstein AAML 80 1,080 0 03 Apr 2018
IoT Security Techniques Based on Machine Learning Liang Xiao Xiaoyue Wan Xiaozhen Lu Yanyong Zhang Di Wu 25 571 0 19 Jan 2018
Spatially Transformed Adversarial Examples Chaowei Xiao Jun-Yan Zhu Yue Liu Warren He M. Liu D. Song AAML 65 520 0 08 Jan 2018
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning Xinyun Chen Chang-rui Liu Yue Liu Kimberly Lu D. Song AAML SILM 82 1,822 0 15 Dec 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 238 11,962 0 19 Jun 2017
Identity Mappings in Deep Residual Networks Kaiming He Xinming Zhang Shaoqing Ren Jian Sun 305 10,149 0 16 Mar 2016
Deep Residual Learning for Image Recognition Kaiming He Xinming Zhang Shaoqing Ren Jian Sun MedIm 1.6K 192,638 0 10 Dec 2015