v1v2 (latest)

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

International Conference on Learning Representations (ICLR), 2021

15 January 2021

ArXiv (abs)PDF HTML Github (122★)

Papers citing "Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks"

50 / 281 papers shown

Title
On the Weaknesses of Backdoor-based Model Watermarking: An Information-theoretic Perspective Aoting Hu Yanzhi Chen Renjie Xie Adrian Weller 207 2 0 10 Sep 2024
NoiseAttack: An Evasive Sample-Specific Multi-Targeted Backdoor Attack Through White Gaussian Noise Abdullah Arafat Miah Kaan Icer Resit Sendag Yu Bi AAML DiffM 165 1 0 03 Sep 2024
Backdoor Defense through Self-Supervised and Generative LearningBritish Machine Vision Conference (BMVC), 2024 Ivan Sabolić Ivan Grubišić Siniša Šegvić AAML 231 1 0 02 Sep 2024
Fisher Information guided Purification against Backdoor AttacksConference on Computer and Communications Security (CCS), 2024 Nazmul Karim Abdullah Al Arafat Adnan Siraj Rakin Zhishan Guo Nazanin Rahnavard AAML 257 5 0 01 Sep 2024
Protecting against simultaneous data poisoning attacksInternational Conference on Learning Representations (ICLR), 2024 Neel Alex Shoaib Ahmed Siddiqui Amartya Sanyal David M. Krueger AAML 232 1 0 23 Aug 2024
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models Yige Li Hanxun Huang Yunhan Zhao Jiabo He Jun Sun AAML SILM 316 19 0 23 Aug 2024
MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup TransferEuropean Conference on Artificial Intelligence (ECAI), 2024 Ming Sun Lihua Jing Zixuan Zhu Rui Wang AAML 108 3 0 22 Aug 2024
A Survey of Trojan Attacks and Defenses to Deep Neural Networks Lingxin Jin Xianyu Wen Wei Jiang Jinyu Zhan AAML 188 3 0 15 Aug 2024
Attacks and Defenses for Generative Diffusion Models: A Comprehensive SurveyACM Computing Surveys (ACM CSUR), 2024 V. T. Truong Luan Ba Dang Long Bao Le DiffM MedIm 302 35 0 06 Aug 2024
Revocable Backdoor for Deep Model TradingEuropean Conference on Artificial Intelligence (ECAI), 2024 Yiran Xu Nan Zhong Zhenxing Qian Xinpeng Zhang AAML 212 1 0 01 Aug 2024
Flatness-aware Sequential Learning Generates Resilient Backdoors Hoang Pham The-Anh Ta Anh Tran Khoa D. Doan FedML AAML 206 1 0 20 Jul 2024
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening Shuyang Cheng Guangyu Shen Kaiyuan Zhang Guanhong Tao Shengwei An Hanxi Guo Shiqing Ma Xiangyu Zhang AAML 200 0 0 16 Jul 2024
Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks Quang H. Nguyen Nguyen Ngoc-Hieu The-Anh Ta Thanh Nguyen-Tang Kok-Seng Wong Hoang Thanh-Tung Khoa D. Doan AAML 275 4 0 15 Jul 2024
Augmented Neural Fine-Tuning for Efficient Backdoor Purification Nazmul Karim Abdullah Al Arafat Umar Khalid Zhishan Guo Nazanin Rahnavard AAML 221 6 0 14 Jul 2024
Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses Yuxin Yang Qiang Li Jinyuan Jia Yuan Hong Binghui Wang AAML FedML 201 19 0 12 Jul 2024
PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning Sizai Hou Songze Li Tayyebeh Jahani-Nezhad Giuseppe Caire FedML 390 7 0 12 Jul 2024
Model-agnostic clean-label backdoor mitigation in cybersecurity environments Giorgio Severi Simona Boboila J. Holodnak K. Kratkiewicz Rauf Izmailov Alina Oprea Alina Oprea AAML 320 1 0 11 Jul 2024
Mitigating Backdoor Attacks using Activation-Guided Model Editing Felix Hsieh H. Nguyen AprilPyone Maungmaung Dmitrii Usynin Isao Echizen AAML KELM LLMSV 212 0 0 10 Jul 2024
Understanding the Gains from Repeated Self-Distillation Divyansh Pareek Simon S. Du Sewoong Oh 271 9 0 05 Jul 2024
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models Yi Zeng Weiyu Sun Tran Ngoc Huynh Dawn Song Bo Li Ruoxi Jia AAML LLMSV 172 42 0 24 Jun 2024
CBPF: Filtering Poisoned Data Based on Composite Backdoor Attack Hanfeng Xia Haibo Hong Ruili Wang AAML 169 0 0 23 Jun 2024
Composite Concept Extraction through BackdooringInternational Conference on Pattern Recognition (ICPR), 2024 Banibrata Ghosh Haripriya Harikumar Khoa D. Doan Svetha Venkatesh Santu Rana 244 0 0 19 Jun 2024
DLP: towards active defense against backdoor attacks with decoupled learning process Zonghao Ying Bin Wu AAML 270 12 0 18 Jun 2024
NBA: defensive distillation for backdoor removal via neural behavior alignment Zonghao Ying Bin Wu AAML 103 13 0 16 Jun 2024
Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey Shang Wang Tianqing Zhu B. Liu Ming Ding Dayong Ye Dayong Ye Wanlei Zhou PILM 297 22 0 12 Jun 2024
Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning Xiaoting Lyu Yufei Han Wei Wang Jingkai Liu Yongsheng Zhu Guangquan Xu Jiqiang Liu Xiangliang Zhang AAML FedML 206 12 0 10 Jun 2024
Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 Xi Li Ruofan Mao Yusen Zhang Renze Lou Chen Wu Jiaqi Wang LRM AAML 405 20 0 10 Jun 2024
PSBD: Prediction Shift Uncertainty Unlocks Backdoor DetectionComputer Vision and Pattern Recognition (CVPR), 2024 Wei Li Pin-Yu Chen Sijia Liu Ren Wang AAML 271 4 0 09 Jun 2024
Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders Tingxu Han Weisong Sun Ziqi Ding Chunrong Fang Hanwei Qian Jiaxun Li Zhenyu Chen Xiangyu Zhang AAML 364 11 0 05 Jun 2024
Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model Jinyin Chen Xiaoming Zhao Haibin Zheng Xiao Li Sheng Xiang Haifeng Guo AAML 140 7 0 01 Jun 2024
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness Weilin Lin Li Liu Shaokui Wei Jianze Li Hui Xiong AAML 210 4 0 30 May 2024
DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person Re-Identification in Real-World Wenli Sun Xinyang Jiang Dongsheng Li Cairong Zhao DiffM AAML 214 2 0 30 May 2024
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks Zhenxing Niu Yuyao Sun Qiguang Miao Rong Jin Gang Hua AAML 204 11 0 28 May 2024
Magnitude-based Neuron Pruning for Backdoor Defens Nan Li Haoyu Jiang Ping Yi AAML 110 3 0 28 May 2024
Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective Nan Li Haiyang Yu Ping Yi AAML 109 1 0 28 May 2024
Partial train and isolate, mitigate backdoor attack Yong Li Han Gao AAML 235 0 0 26 May 2024
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack Mingli Zhu Siyuan Liang Baoyuan Wu AAML 352 23 0 25 May 2024
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor Shaokui Wei Hongyuan Zha Baoyuan Wu AAML 207 7 0 25 May 2024
Invisible Backdoor Attack against Self-supervised LearningComputer Vision and Pattern Recognition (CVPR), 2024 Hanrong Zhang Zhenting Wang Tingxu Han Haoyang Ling Chenlu Zhan Jundong Li Hongwei Wang Shiqing Ma Hongwei Wang Shiqing Ma AAML SSL 249 1 0 23 May 2024
Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and RelearningIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2024 Nay Myat Min Long H. Pham Jun Sun MU AAML 271 1 0 23 May 2024
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks Boheng Li Yishuo Cai Haowei Li Feng Xue Zhifeng Li Yiming Li MQ AAML 231 28 0 21 May 2024
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers Shengyuan Yang Jiawang Bai Kuofeng Gao Yong-Liang Yang Yiming Li Shu-Tao Xia AAML SILM 279 5 0 17 May 2024
Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive TriggersInternational Joint Conference on Artificial Intelligence (IJCAI), 2024 Binxiao Huang Jason Chun Lok Li Chang Liu Ngai Wong AAML 258 2 0 09 May 2024
Unlearning Backdoor Attacks through Gradient-Based Model Pruning Kealan Dunnett Reza Arablouei Dimity Miller Volkan Dedeoglu Raja Jurdak AAML 208 1 0 07 May 2024
The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data Zixuan Zhu Rui Wang Cong Zou Lihua Jing AAML FedML 225 5 0 17 Apr 2024
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning Shuyang Cheng Guanhong Tao Yingqi Liu Guangyu Shen Shengwei An Shiwei Feng Xiangzhe Xu Kaiyuan Zhang Shiqing Ma Xiangyu Zhang AAML 201 9 0 25 Mar 2024
An Embarrassingly Simple Defense Against Backdoor Attacks On SSLIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 Aryan Satpathy Nilaksh Nilaksh D. Rajwade AAML 136 0 0 23 Mar 2024
Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices Sara Abdali Richard Anarfi C. Barberan Jia He Erfan Shayegani PILM 373 45 0 19 Mar 2024
Invisible Backdoor Attack Through Singular Value DecompositionChinese Conference on Pattern Recognition and Computer Vision (CPRCV), 2024 Wenmin Chen Xiaowei Xu AAML 200 2 0 18 Mar 2024
Impart: An Imperceptible and Effective Label-Specific Backdoor Attack Jingke Zhao Zan Wang Yongwei Wang Lanjun Wang AAML 62 0 0 18 Mar 2024