Adversarial Neuron Pruning Purifies Backdoored Deep Models

27 October 2021

Papers citing "Adversarial Neuron Pruning Purifies Backdoored Deep Models"

50 / 184 papers shown

Title
BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection Tinghao Xie Xiangyu Qi Ping He Yiming Li Jiachen T. Wang Prateek Mittal AAML 25 9 0 23 Aug 2023
Protect Federated Learning Against Backdoor Attacks via Data-Free Trigger Generation Yanxin Yang Ming Hu Yue Cao Jun Xia Yihao Huang Yang Liu Mingsong Chen FedML 29 6 0 22 Aug 2023
Temporal-Distributed Backdoor Attack Against Video Based Action Recognition Xi Li Songhe Wang Rui Huang Mahanth K. Gowda G. Kesidis AAML 39 6 0 21 Aug 2023
Backdoor Mitigation by Correcting the Distribution of Neural Activations Xi Li Zhen Xiang David J. Miller G. Kesidis AAML 13 0 0 18 Aug 2023
Test-Time Backdoor Defense via Detecting and Repairing Jiyang Guan Jian Liang Ran He AAML 33 0 0 11 Aug 2023
XGBD: Explanation-Guided Graph Backdoor Detection Zihan Guan Mengnan Du Ninghao Liu AAML 29 9 0 08 Aug 2023
Backdoor Federated Learning by Poisoning Backdoor-Critical Layers Haomin Zhuang Mingxian Yu Hao Wang Yang Hua Jian Li Xu Yuan FedML 26 9 0 08 Aug 2023
Beating Backdoor Attack at Its Own Game Min Liu Alberto L. Sangiovanni-Vincentelli Xiangyu Yue AAML 65 11 0 28 Jul 2023
Samplable Anonymous Aggregation for Private Federated Data Analysis Kunal Talwar Shan Wang Audra McMillan Vojta Jina Vitaly Feldman ... Congzheng Song Karl Tarbe Sebastian Vogt L. Winstrom Shundong Zhou FedML 38 13 0 27 Jul 2023
Backdoor Attacks against Voice Recognition Systems: A Survey Baochen Yan Jiahe Lan Zheng Yan AAML 30 8 0 23 Jul 2023
Adversarial Feature Map Pruning for Backdoor Dong Huang Qingwen Bu AAML 35 4 0 21 Jul 2023
Neuron Sensitivity Guided Test Case Selection for Deep Learning Testing Dong Huang Qi Bu Yichao Fu Yuhao Qing Junjie Chen Heming Cui AAML 34 2 0 20 Jul 2023
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples Shaokui Wei Mingda Zhang H. Zha Baoyuan Wu TPM 18 35 0 20 Jul 2023
Efficient Backdoor Removal Through Natural Gradient Fine-tuning Nazmul Karim Abdullah Al Arafat Umar Khalid Zhishan Guo Naznin Rahnavard AAML 26 1 0 30 Jun 2023
Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features Mingli Zhu Shaokui Wei H. Zha Baoyuan Wu AAML 30 37 0 29 Jun 2023
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks Ziqiang Li Hong Sun Pengfei Xia Beihao Xia Xue Rui Wei Zhang Qinglang Guo Bin Li AAML 32 8 0 14 Jun 2023
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers Ruotong Wang Hongrui Chen Zihao Zhu Li Liu Baoyuan Wu DiffM 30 11 0 01 Jun 2023
UMD: Unsupervised Model Detection for X2X Backdoor Attacks Zhen Xiang Zidi Xiong Bo-wen Li AAML 26 20 0 29 May 2023
Differentially-Private Decision Trees and Provable Robustness to Data Poisoning D. Vos Jelle Vos Tianyu Li Z. Erkin S. Verwer FedML 16 1 0 24 May 2023
Reconstructive Neuron Pruning for Backdoor Defense Yige Li X. Lyu Xingjun Ma Nodens Koren Lingjuan Lyu Bo-wen Li Yugang Jiang AAML 32 42 0 24 May 2023
Backdoor Attack with Sparse and Invisible Trigger Yinghua Gao Yiming Li Xueluan Gong Zhifeng Li Shutao Xia Qianqian Wang AAML 13 20 0 11 May 2023
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks Nils Lukas Florian Kerschbaum 36 1 0 07 May 2023
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization Mingli Zhu Shaokui Wei Li Shen Yanbo Fan Baoyuan Wu AAML 36 51 0 24 Apr 2023
UNICORN: A Unified Backdoor Trigger Inversion Framework Zhenting Wang Kai Mei Juan Zhai Shiqing Ma LLMSV 32 44 0 05 Apr 2023
Detecting Backdoors in Pre-trained Encoders Shiwei Feng Guanhong Tao Shuyang Cheng Guangyu Shen Xiangzhe Xu Yingqi Liu Kaiyuan Zhang Shiqing Ma Xiangyu Zhang 82 47 0 23 Mar 2023
Backdoor Defense via Adaptively Splitting Poisoned Dataset Kuofeng Gao Yang Bai Jindong Gu Yong-Liang Yang Shutao Xia AAML 26 49 0 23 Mar 2023
Black-box Backdoor Defense via Zero-shot Image Purification Yucheng Shi Mengnan Du Xuansheng Wu Zihan Guan Jin Sun Ninghao Liu 40 28 0 21 Mar 2023
Influencer Backdoor Attack on Semantic Segmentation Haoheng Lan Jindong Gu Philip Torr Hengshuang Zhao AAML 26 6 0 21 Mar 2023
AdaptGuard: Defending Against Universal Attacks for Model Adaptation Lijun Sheng Jian Liang Ran He Zilei Wang Tien-Ping Tan AAML 48 5 0 19 Mar 2023
CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning Hritik Bansal Nishad Singhi Yu Yang Fan Yin Aditya Grover Kai-Wei Chang AAML 34 42 0 06 Mar 2023
FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases Chong Fu Xuhong Zhang S. Ji Ting Wang Peng Lin Yanghe Feng Jianwei Yin AAML 43 10 0 28 Feb 2023
SATBA: An Invisible Backdoor Attack Based On Spatial Attention Huasong Zhou Xiaowei Xu Zhenyu Wang Leon Bevan Bullock AAML 27 1 0 25 Feb 2023
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models Max Lamparth Anka Reuel KELM 36 10 0 24 Feb 2023
Poisoning Web-Scale Training Datasets is Practical Nicholas Carlini Matthew Jagielski Christopher A. Choquette-Choo Daniel Paleka Will Pearce Hyrum S. Anderson Andreas Terzis Kurt Thomas Florian Tramèr SILM 31 182 0 20 Feb 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 21 95 0 07 Feb 2023
Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks Zeyu Qin Liuyi Yao Daoyuan Chen Yaliang Li Bolin Ding Minhao Cheng FedML 38 25 0 03 Feb 2023
Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attacks Xiaoyun Xu Oguzhan Ersoy S. Picek AAML 26 2 0 01 Feb 2023
BackdoorBox: A Python Toolbox for Backdoor Learning Yiming Li Mengxi Ya Yang Bai Yong Jiang Shutao Xia AAML 44 40 0 01 Feb 2023
Distilling Cognitive Backdoor Patterns within an Image Hanxun Huang Xingjun Ma S. Erfani James Bailey AAML 34 24 0 26 Jan 2023
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense Shuyang Cheng Guanhong Tao Yingqi Liu Shengwei An Xiangzhe Xu ... Guangyu Shen Kaiyuan Zhang Qiuling Xu Shiqing Ma Xiangyu Zhang AAML 24 14 0 16 Jan 2023
Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition Hasan Hammoud Shuming Liu Mohammad Alkhrashi Fahad Albalawi Guohao Li AAML 32 8 0 03 Jan 2023
How to Backdoor Diffusion Models? Sheng-Yen Chou Pin-Yu Chen Tsung-Yi Ho DiffM SILM 19 95 0 11 Dec 2022
Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning Marissa Connor Vincent Emanuele SILM AAML 17 1 0 05 Dec 2022
Backdoor Vulnerabilities in Normally Trained Deep Learning Models Guanhong Tao Zhenting Wang Shuyang Cheng Shiqing Ma Shengwei An Yingqi Liu Guangyu Shen Zhuo Zhang Yunshu Mao Xiangyu Zhang SILM 19 17 0 29 Nov 2022
Backdoor Cleansing with Unlabeled Data Lu Pang Tao Sun Haibin Ling Chao Chen AAML 37 18 0 22 Nov 2022
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification Wenli Sun Xinyang Jiang Shuguang Dou Dongsheng Li Duoqian Miao Cheng Deng Cairong Zhao AAML 29 8 0 20 Nov 2022
Backdoor Attacks on Time Series: A Generative Approach Yujing Jiang Xingjun Ma S. Erfani James Bailey AAML AI4TS 28 12 0 15 Nov 2022
M-to-N Backdoor Paradigm: A Multi-Trigger and Multi-Target Attack to Deep Learning Models Linshan Hou Zhongyun Hua Yuhong Li Yifeng Zheng Leo Yu Zhang AAML 26 2 0 03 Nov 2022
Untargeted Backdoor Attack against Object Detection C. Luo Yiming Li Yong Jiang Shutao Xia AAML 28 31 0 02 Nov 2022
Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class Khoa D. Doan Yingjie Lao Ping Li 34 40 0 17 Oct 2022