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
Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks Yaxin Xiao Qingqing Ye Zi Liang Haoyang Li Ronghua Li Huadi Zheng Haibo Hu AAML 139 0 0 11 Nov 2025
Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning Bingqi Shang Yiwei Chen Yihua Zhang Bingquan Shen Sijia Liu MU KELM AAML 188 0 0 19 Oct 2025
Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models Guanbin Li Miao Yu Moayad Aloqaily Zhenhong Zhou Kun Wang Linsey Pang Prakhar Mehrotra Qingsong Wen AAML 68 0 0 11 Oct 2025
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples Alexandra Souly Javier Rando Ed Chapman Xander Davies Shae McFadden ... Erik Jones Chris Hicks Nicholas Carlini Y. Gal Robert Kirk AAML SILM 220 8 0 08 Oct 2025
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack Yukun Chen Boheng Li Yu Yuan Leyi Qi Y. Li Tianwei Zhang Zhan Qin K. Ren AAML 88 1 0 28 Sep 2025
Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution Chen Chen Yuchen Sun Jiaxin Gao Xueluan Gong Qian-Wei Wang Ziyao Wang Yongsen Zheng K. Lam AAML KELM 124 0 0 28 Aug 2025
From Detection to Correction: Backdoor-Resilient Face Recognition via Vision-Language Trigger Detection and Noise-Based Neutralization Farah Wahida M. Chamikara Yashothara Shanmugarasa Mohan Baruwal Chhetri Thilina Ranbaduge Ibrahim Khalil AAML 84 0 0 07 Aug 2025
NT-ML: Backdoor Defense via Non-target Label Training and Mutual Learning Wenjie Huo Katinka Wolter AAML 88 0 0 07 Aug 2025
BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models Yu Pan Jiahao Chen Lin Wang Bingrong Dai Yi Du AAML DiffM 214 0 0 05 Aug 2025
Evading Data Provenance in Deep Neural Networks Hongyu Zhu Sichu Liang Wenwen Wang Zhuomeng Zhang Fangqi Li Shi-Lin Wang AAML 227 1 0 01 Aug 2025
PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning Xiangman Li Xiaodong Wu Jianbing Ni Mohamed Mahmoud Maazen Alsabaan AAML 147 0 0 18 Jun 2025
Circumventing Backdoor Space via Weight Symmetry Jie Peng Hongwei Yang Jing Zhao Hengji Dong Hui He Weizhe Zhang Haoyu He AAML 188 0 0 09 Jun 2025
Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies Chenruo Liu Kenan Tang Yao Qin Qi Lei 230 1 0 28 May 2025
BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution Ji Guo Xiaolei Wen Wenbo Jiang Cheng Huang Jinjin Li Hongwei Li 198 0 0 21 May 2025
Where the Devil Hides: Deepfake Detectors Can No Longer Be TrustedComputer Vision and Pattern Recognition (CVPR), 2025 Shuaiwei Yuan Junyu Dong Yuezun Li AAML 257 2 0 13 May 2025
Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models Kuofeng Gao Yufei Zhu Yiming Li Jiawang Bai Yong-Liang Yang Zerui Li Shu-Tao Xia 224 0 0 05 May 2025
Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric TasksComputer Vision and Pattern Recognition (CVPR), 2025 Yu Zhou Dian Zheng Qijie Mo Renjie Lu Kun-Yu Lin Wei-Shi Zheng MU 231 9 0 31 Mar 2025
Prototype Guided Backdoor Defense Venkat Adithya Amula Sunayana Samavedam Saurabh Saini Avani Gupta Narayanan P J AAML 248 1 0 26 Mar 2025
Lie Detector: Unified Backdoor Detection via Cross-Examination Framework Xiaobei Wang Yaning Tan Dongping Liao Han Fang Aishan Liu Simeng Qin Yu-liang Lu E. Chang X. Gao AAML 305 3 0 21 Mar 2025
Seal Your Backdoor with Variational Defense Ivan Sabolić Matej Grcić Sinisa Segvic AAML 1.1K 1 0 11 Mar 2025
SecureGaze: Defending Gaze Estimation Against Backdoor AttacksACM International Conference on Embedded Networked Sensor Systems (SenSys), 2025 Lingyu Du Yupei Liu Jinyuan Jia Guohao Lan AAML 174 0 0 27 Feb 2025
Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP Jiawei Kong Hao Fang Sihang Guo Chenxi Qing Bin Chen Bin Wang Shu-Tao Xia Ke Xu AAML VLM 324 0 0 26 Feb 2025
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features Mingli Zhu Shaokui Wei Hongyuan Zha Baoyuan Wu AAML 291 1 0 23 Feb 2025
REFINE: Inversion-Free Backdoor Defense via Model ReprogrammingInternational Conference on Learning Representations (ICLR), 2025 Yuxiao Chen Shuo Shao Enhao Huang Yiming Li Pin-Yu Chen Zhan Qin Kui Ren AAML 213 15 0 22 Feb 2025
A Robust Attack: Displacement Backdoor Attack Yong Li Han Gao AAML 205 0 0 14 Feb 2025
Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning Mingyuan Fan Zhanyi Hu Fuyi Wang Cen Chen SILM 245 1 0 22 Jan 2025
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning Zhifang Zhang Shuo He Bingquan Shen Bingquan Shen Lei Feng AAML 491 4 0 29 Dec 2024
Backdoor Attack with Invisible Triggers Based on Model Architecture Modification Yuan Ma Jiankang Wei Jiankang Wei Jinmeng Tang Xiaoyu Zhang 398 0 0 22 Dec 2024
UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion ModelsComputer Vision and Pattern Recognition (CVPR), 2024 Yuning Han Bingyin Zhao Rui Chu Feng Luo Biplab Sikdar Yingjie Lao DiffM AAML 465 4 0 16 Dec 2024
FLARE: Toward Universal Dataset Purification against Backdoor AttacksIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2024 Linshan Hou Wei Luo Zhongyun Hua Songhua Chen L. Zhang Yiming Li AAML 418 4 0 29 Nov 2024
LADDER: Multi-objective Backdoor Attack via Evolutionary AlgorithmNetwork and Distributed System Security Symposium (NDSS), 2024 Dazhuang Liu Yanqi Qiao Rui Wang K. Liang Georgios Smaragdakis AAML 290 0 0 28 Nov 2024
Neutralizing Backdoors through Information Conflicts for Large Language Models Chen Chen Yuchen Sun Xueluan Gong Jiaxin Gao K. Lam KELM AAML 340 3 0 27 Nov 2024
BadScan: An Architectural Backdoor Attack on Visual State Space Models Om Suhas Deshmukh Sankalp Nagaonkar A. Tripathi Ashish Mishra Mamba 251 0 0 26 Nov 2024
Delta-Influence: Unlearning Poisons via Influence Functions Wenjie Li Jiawei Li Christian Schroeder de Witt Christian Schroeder de Witt Amartya Sanyal Amartya Sanyal MU TDI 395 9 0 20 Nov 2024
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Nay Myat Min Long H. Pham Yige Li Jun Sun AAML 365 10 0 18 Nov 2024
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense EvaluationKnowledge Discovery and Data Mining (KDD), 2024 Haiyang Yu Tian Xie Jiaping Gui Pengyang Wang P. Yi Yue Wu 282 2 0 17 Nov 2024
On the Surprising Effectiveness of Attention Transfer for Vision TransformersNeural Information Processing Systems (NeurIPS), 2024 Alexander C. Li Yuandong Tian Bin Chen Deepak Pathak Xinlei Chen 181 8 0 14 Nov 2024
Identify Backdoored Model in Federated Learning via Individual UnlearningIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2024 Jiahao Xu Zikai Zhang Rui Hu FedML AAML 317 4 0 01 Nov 2024
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models Yige Li Hanxun Huang Jiaming Zhang Xingjun Ma Yu-Gang Jiang AAML 122 2 0 25 Oct 2024
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing Dongliang Guo Mengxuan Hu Zihan Guan Junfeng Guo Thomas Hartvigsen Sheng Li AAML 300 4 0 23 Oct 2024
LLMScan: Causal Scan for LLM Misbehavior Detection Mengdi Zhang Kai Kiat Goh Peixin Zhang Jun Sun Rose Lin Xin Hongyu Zhang 511 3 0 22 Oct 2024
Generalized Adversarial Code-Suggestions: Exploiting Contexts of LLM-based Code-CompletionACM Asia Conference on Computer and Communications Security (AsiaCCS), 2024 Karl Rubel Maximilian Noppel Christian Wressnegger AAML SILM 163 0 0 14 Oct 2024
Invisibility Cloak: Disappearance under Human Pose Estimation via Backdoor Attacks Minxing Zhang Wenshu Fan Xiao Zhang Shui Yu Michael Backes Xiao Zhang AAML 273 1 0 10 Oct 2024
"No Matter What You Do": Purifying GNN Models via Backdoor Unlearning Jiale Zhang Chengcheng Zhu Bosen Rao Hao Sui Xiaobing Sun Bing Chen Chunyi Zhou Shouling Ji AAML 175 0 0 02 Oct 2024
Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers Zeyu Michael Li AAML 215 0 0 01 Oct 2024
Psychometrics for Hypnopaedia-Aware Machinery via Chaotic Projection of Artificial Mental Imagery Ching-Chun Chang Kai Gao Shuying Xu Anastasia Kordoni Christopher Leckie Isao Echizen 143 0 0 29 Sep 2024
IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Method Chaohui Xu Qi Cui Jinxin Dong Weiyang He Chip-Hong Chang AAML 379 3 0 29 Sep 2024
Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency AnalysisInternational Conference on Pattern Recognition (ICPR), 2024 Xianda Zhang Siyuan Liang AAML 171 2 0 24 Sep 2024
Adversarial Backdoor Defense in CLIP Junhao Kuang Yaning Tan Jiawei Liang Kuanrong Liu Xiaochun Cao AAML 197 8 0 24 Sep 2024
PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning Yukai Xu Yujie Gu Kouichi Sakurai AAML 110 1 0 18 Sep 2024