Anti-Backdoor Learning: Training Clean Models on Poisoned Data

22 October 2021

Papers citing "Anti-Backdoor Learning: Training Clean Models on Poisoned Data"

50 / 206 papers shown

Title
Potion: Towards Poison Unlearning Stefan Schoepf Jack Foster Alexandra Brintrup AAML MU 47 7 0 13 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 51 6 0 10 Jun 2024
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection Wei Li Pin-Yu Chen Sijia Liu Ren Wang AAML 43 3 0 09 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 45 2 0 30 May 2024
BAN: Detecting Backdoors Activated by Adversarial Neuron Noise Xiaoyun Xu Zhuoran Liu Stefanos Koffas Shujian Yu S. Picek AAML 32 1 0 30 May 2024
PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models Omead Brandon Pooladzandi Jeffrey Q. Jiang Sunay Bhat Gregory Pottie AAML 31 0 0 28 May 2024
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics Sunay Bhat Jeffrey Q. Jiang Omead Brandon Pooladzandi Alexander Branch Gregory Pottie AAML 32 2 0 28 May 2024
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks Zhenxing Niu Yuyao Sun Qiguang Miao Rong Jin Gang Hua AAML 38 6 0 28 May 2024
Magnitude-based Neuron Pruning for Backdoor Defens Nan Li Haoyu Jiang Ping Yi AAML 19 1 0 28 May 2024
Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective Nan Li Haiyang Yu Ping Yi AAML 28 0 0 28 May 2024
Partial train and isolate, mitigate backdoor attack Yong Li Han Gao AAML 29 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 42 14 0 25 May 2024
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor Shaokui Wei Hongyuan Zha Baoyuan Wu AAML 53 3 0 25 May 2024
Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning Nay Myat Min Long H. Pham Jun Sun MU AAML 32 0 0 23 May 2024
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks Xuanli He Qiongkai Xu Jun Wang Benjamin I. P. Rubinstein Trevor Cohn AAML 42 4 0 19 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 35 5 0 17 May 2024
IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency Linshan Hou Ruili Feng Zhongyun Hua Wei Luo Leo Yu Zhang Yiming Li AAML 43 19 0 16 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 31 3 0 17 Apr 2024
UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models Zihan Guan Mengxuan Hu Sheng R. Li Anil Vullikanti DiffM AAML 39 3 0 01 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 32 3 0 25 Mar 2024
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion Hossein Souri Arpit Bansal Hamid Kazemi Liam H. Fowl Aniruddha Saha Jonas Geiping Andrew Gordon Wilson Rama Chellappa Tom Goldstein Micah Goldblum SILM DiffM 21 1 0 25 Mar 2024
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning Siyuan Liang Kuanrong Liu Jiajun Gong Jiawei Liang Yuan Xun Ee-Chien Chang Xiaochun Cao AAML MU 29 13 0 24 Mar 2024
Have You Poisoned My Data? Defending Neural Networks against Data Poisoning Fabio De Gaspari Dorjan Hitaj Luigi V. Mancini AAML TDI 19 4 0 20 Mar 2024
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency Soumyadeep Pal Yuguang Yao Ren Wang Bingquan Shen Sijia Liu AAML 36 8 0 15 Mar 2024
Backdoor Attack with Mode Mixture Latent Modification Hongwei Zhang Xiaoyin Xu Dongsheng An Xianfeng Gu Min Zhang AAML 21 0 0 12 Mar 2024
A general approach to enhance the survivability of backdoor attacks by decision path coupling Yufei Zhao Dingji Wang Bihuan Chen Ziqian Chen Xin Peng AAML 19 0 0 05 Mar 2024
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge Ansh Arora Xuanli He Maximilian Mozes Srinibas Swain Mark Dras Qiongkai Xu SILM MoMe AAML 58 12 0 29 Feb 2024
Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks A. Unnervik Hatef Otroshi-Shahreza Anjith George S´ebastien Marcel AAML SILM 32 0 0 28 Feb 2024
Model X-ray:Detect Backdoored Models via Decision Boundary Yanghao Su Jie Zhang Ting Xu Tianwei Zhang Weiming Zhang Neng H. Yu AAML 47 1 0 27 Feb 2024
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem Georg Pichler Marco Romanelli Divya Prakash Manivannan P. Krishnamurthy Farshad Khorrami Siddharth Garg 25 2 0 26 Feb 2024
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space Zongru Wu Zhuosheng Zhang Pengzhou Cheng Gongshen Liu AAML 44 4 0 19 Feb 2024
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection Jiawei Liang Siyuan Liang Aishan Liu Xiaojun Jia Junhao Kuang Xiaochun Cao AAML 24 20 0 18 Feb 2024
Instruction Backdoor Attacks Against Customized LLMs Rui Zhang Hongwei Li Rui Wen Wenbo Jiang Yuan Zhang Michael Backes Yun Shen Yang Zhang AAML SILM 30 21 0 14 Feb 2024
Rethinking Machine Unlearning for Large Language Models Sijia Liu Yuanshun Yao Jinghan Jia Stephen Casper Nathalie Baracaldo ... Hang Li Kush R. Varshney Mohit Bansal Sanmi Koyejo Yang Liu AILaw MU 70 81 0 13 Feb 2024
Test-Time Backdoor Attacks on Multimodal Large Language Models Dong Lu Tianyu Pang Chao Du Qian Liu Xianjun Yang Min-Bin Lin AAML 53 21 0 13 Feb 2024
Preference Poisoning Attacks on Reward Model Learning Junlin Wu Jiong Wang Chaowei Xiao Chenguang Wang Ning Zhang Yevgeniy Vorobeychik AAML 24 5 0 02 Feb 2024
Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance Wenqi Wei Ling Liu 25 16 0 02 Feb 2024
Multi-Trigger Backdoor Attacks: More Triggers, More Threats Yige Li Xingjun Ma Jiabo He Hanxun Huang Yu-Gang Jiang AAML 28 5 0 27 Jan 2024
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning Baoyuan Wu Hongrui Chen Mingda Zhang Zihao Zhu Shaokui Wei Danni Yuan Mingli Zhu Ruotong Wang Li Liu Chaoxiao Shen AAML ELM 72 9 0 26 Jan 2024
WPDA: Frequency-based Backdoor Attack with Wavelet Packet Decomposition Zhengyao Song Yongqiang Li Danni Yuan Li Liu Shaokui Wei Baoyuan Wu AAML 32 4 0 24 Jan 2024
End-to-End Anti-Backdoor Learning on Images and Time Series Yujing Jiang Xingjun Ma S. Erfani Yige Li James Bailey 40 1 0 06 Jan 2024
Progressive Poisoned Data Isolation for Training-time Backdoor Defense Yiming Chen Haiwei Wu Jiantao Zhou AAML 32 9 0 20 Dec 2023
DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models Jiachen Zhou Peizhuo Lv Yibing Lan Guozhu Meng Kai Chen Hualong Ma AAML 21 7 0 18 Dec 2023
A Comprehensive Survey of Attack Techniques, Implementation, and Mitigation Strategies in Large Language Models Aysan Esmradi Daniel Wankit Yip C. Chan AAML 32 11 0 18 Dec 2023
UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks Bingyin Zhao Yingjie Lao AAML 22 1 0 17 Dec 2023
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks Changjiang Li Ren Pang Bochuan Cao Zhaohan Xi Jinghui Chen Shouling Ji Ting Wang AAML 36 6 0 14 Dec 2023
Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey Yichen Wan Youyang Qu Wei Ni Yong Xiang Longxiang Gao Ekram Hossain AAML 47 33 0 14 Dec 2023
Defenses in Adversarial Machine Learning: A Survey Baoyuan Wu Shaokui Wei Mingli Zhu Meixi Zheng Zihao Zhu Mingda Zhang Hongrui Chen Danni Yuan Li Liu Qingshan Liu AAML 30 14 0 13 Dec 2023
Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks Danni Yuan Shaokui Wei Mingda Zhang Li Liu Baoyuan Wu AAML 40 5 0 11 Dec 2023
BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting Huming Qiu Junjie Sun Mi Zhang Xudong Pan Min Yang AAML 34 4 0 08 Dec 2023