Adversarial Neuron Pruning Purifies Backdoored Deep Models

27 October 2021

Papers citing "Adversarial Neuron Pruning Purifies Backdoored Deep Models"

50 / 184 papers shown

Title
Propaganda via AI? A Study on Semantic Backdoors in Large Language Models Nay Myat Min Long H. Pham Yige Li Jun Sun AAML 30 0 0 15 Apr 2025
Defending Deep Neural Networks against Backdoor Attacks via Module Switching Weijun Li Ansh Arora Xuanli He Mark Dras Qiongkai Xu AAML MoMe 53 0 0 08 Apr 2025
DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data Dorde Popovic Amin Sadeghi Ting Yu Sanjay Chawla Issa M. Khalil AAML 49 0 0 27 Mar 2025
Prototype Guided Backdoor Defense Venkat Adithya Amula Sunayana Samavedam Saurabh Saini Avani Gupta Narayanan P J AAML 50 0 0 26 Mar 2025
Seal Your Backdoor with Variational Defense Ivan Sabolić Matej Grcić Sinisa Segvic AAML 159 0 0 11 Mar 2025
NaviDet: Efficient Input-level Backdoor Detection on Text-to-Image Synthesis via Neuron Activation Variation Shengfang Zhai Jiajun Li Yue Liu Huanran Chen Zhihua Tian Wenjie Qu Qingni Shen Ruoxi Jia Yinpeng Dong Jiaheng Zhang AAML 49 0 0 09 Mar 2025
SecureGaze: Defending Gaze Estimation Against Backdoor Attacks Lingyu Du Yupei Liu Jinyuan Jia Guohao Lan AAML 33 0 0 27 Feb 2025
Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in Pre-trained Vision-Language Models Jiawei Kong Hao Fang Sihang Guo Chenxi Qing Bin Chen Bin Wang Shu-Tao Xia AAML VLM 90 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 44 0 0 23 Feb 2025
BackdoorDM: A Comprehensive Benchmark for Backdoor Learning in Diffusion Model Weilin Lin Nanjun Zhou Y. Wang Jianze Li Hui Xiong Li Liu AAML DiffM 175 0 0 17 Feb 2025
MADE: Graph Backdoor Defense with Masked Unlearning Xiao Lin amd Mingjie Li Mingjie Li Yisen Wang AAML 95 1 0 03 Jan 2025
Cut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution Yao Tong Weijun Li Xuanli He Haolan Zhan Qiongkai Xu AAML 35 1 0 31 Dec 2024
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning Zhifang Zhang Shuo He Bingquan Shen Lei Feng Lei Feng AAML 55 0 0 29 Dec 2024
A Backdoor Attack Scheme with Invisible Triggers Based on Model Architecture Modification Yuan Ma Xu Ma Jiankang Wei Jinmeng Tang Xiaoyu Zhang Yilun Lyu Kehao Chen Jingtong Huang 88 0 0 22 Dec 2024
UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models Yuning Han Bingyin Zhao Rui Chu Feng Luo Biplab Sikdar Yingjie Lao DiffM AAML 86 1 0 16 Dec 2024
Data Free Backdoor Attacks Bochuan Cao Jinyuan Jia Chuxuan Hu Wenbo Guo Zhen Xiang Jinghui Chen Bo-wen Li Dawn Song AAML 81 0 0 09 Dec 2024
Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior Yi Yu Yufei Wang Wenhan Yang Lanqing Guo Shijian Lu Ling-yu Duan Yap-Peng Tan Alex C. Kot AAML 86 4 0 02 Dec 2024
FLARE: Towards Universal Dataset Purification against Backdoor Attacks Linshan Hou Wei Luo Zhongyun Hua Songhua Chen L. Zhang Yiming Li AAML 72 0 0 29 Nov 2024
Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Alvi Md Ishmam Christopher Thomas AAML 121 3 0 23 Nov 2024
Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization Mingda Zhang Mingli Zhu Zihao Zhu Baoyuan Wu AAML 78 1 0 18 Nov 2024
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Nay Myat Min Long H. Pham Yige Li Tianlong Chen AAML 66 4 0 18 Nov 2024
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation Haiyang Yu Tian Xie Jiaping Gui Pengyang Wang P. Yi Yue Wu 53 1 0 17 Nov 2024
Defending Deep Regression Models against Backdoor Attacks Lingyu Du Yupei Liu Jinyuan Jia Guohao Lan AAML 31 1 0 07 Nov 2024
Identify Backdoored Model in Federated Learning via Individual Unlearning Jiahao Xu Zikai Zhang Rui Hu FedML AAML 62 1 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 35 2 0 25 Oct 2024
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace Jinluan Yang Anke Tang Didi Zhu Zhengyu Chen Li Shen Fei Wu MoMe AAML 62 3 0 17 Oct 2024
Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning Hassan Ali Surya Nepal S. Kanhere S. Jha AAML FedML 26 1 0 15 Oct 2024
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense Rui Min Zeyu Qin Nevin L. Zhang Li Shen Minhao Cheng AAML 36 4 0 13 Oct 2024
Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers Zeyu Michael Li AAML 26 0 0 01 Oct 2024
BadHMP: Backdoor Attack against Human Motion Prediction Chaohui Xu Si Wang Chip-Hong Chang AAML 35 0 0 29 Sep 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 24 0 0 29 Sep 2024
Adversarial Backdoor Defense in CLIP Junhao Kuang Siyuan Liang Jiawei Liang Kuanrong Liu Xiaochun Cao AAML 36 2 0 24 Sep 2024
Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm Jaehan Kim Minkyoo Song S. Na Seungwon Shin AAML 35 0 0 21 Sep 2024
Data Poisoning and Leakage Analysis in Federated Learning Wenqi Wei Tiansheng Huang Zachary Yahn Anoop Singhal Margaret Loper Ling Liu FedML SILM 33 0 0 19 Sep 2024
On the Weaknesses of Backdoor-based Model Watermarking: An Information-theoretic Perspective Aoting Hu Yanzhi Chen Renjie Xie Adrian Weller 38 0 0 10 Sep 2024
TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors Yichuan Mo Hui Huang Mingjie Li Ang Li Yisen Wang AAML DiffM 32 16 0 09 Sep 2024
Fisher Information guided Purification against Backdoor Attacks Nazmul Karim Abdullah Al Arafat Adnan Siraj Rakin Zhishan Guo Nazanin Rahnavard AAML 51 1 0 01 Sep 2024
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation Weilin Lin Li Liu Jianze Li Hui Xiong AAML 51 1 0 28 Aug 2024
VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification Yungi Cho Woorim Han Miseon Yu Younghan Lee Ho Bae Y. Paek AAML FedML 32 0 0 28 Aug 2024
Protecting against simultaneous data poisoning attacks Neel Alex Shoaib Ahmed Siddiqui Amartya Sanyal David M. Krueger AAML 42 1 0 23 Aug 2024
Mitigating Backdoor Attacks in Federated Learning via Flipping Weight Updates of Low-Activation Input Neurons Binbin Ding Penghui Yang Zeqing Ge Shengjun Huang AAML FedML 39 0 0 16 Aug 2024
BadMerging: Backdoor Attacks Against Model Merging Jinghuai Zhang Jianfeng Chi Zheng Li Kunlin Cai Yang Zhang Yuan Tian MoMe FedML AAML 44 14 0 14 Aug 2024
Revocable Backdoor for Deep Model Trading Yiran Xu Nan Zhong Zhenxing Qian Xinpeng Zhang AAML 35 0 0 01 Aug 2024
Flatness-aware Sequential Learning Generates Resilient Backdoors Hoang Pham The-Anh Ta Anh Tran Khoa D. Doan FedML AAML 36 0 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 31 0 0 16 Jul 2024
Augmented Neural Fine-Tuning for Efficient Backdoor Purification Nazmul Karim Abdullah Al Arafat Umar Khalid Zhishan Guo Nazanin Rahnavard AAML 40 0 0 14 Jul 2024
CBPF: Filtering Poisoned Data Based on Composite Backdoor Attack Hanfeng Xia Haibo Hong Ruili Wang AAML 63 0 0 23 Jun 2024
Composite Concept Extraction through Backdooring Banibrata Ghosh Haripriya Harikumar Khoa D. Doan Svetha Venkatesh Santu Rana 31 0 0 19 Jun 2024
DLP: towards active defense against backdoor attacks with decoupled learning process Zonghao Ying Bin Wu AAML 46 6 0 18 Jun 2024
CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models Yuetai Li Zhangchen Xu Fengqing Jiang Luyao Niu D. Sahabandu Bhaskar Ramasubramanian Radha Poovendran SILM AAML 62 7 0 18 Jun 2024