Not All Poisons are Created Equal: Robust Training against Data Poisoning

18 October 2022

Yu Yang

Tianwei Liu

Baharan Mirzasoleiman

AAML

ArXiv (abs)PDF HTML

Papers citing "Not All Poisons are Created Equal: Robust Training against Data Poisoning"

26 / 26 papers shown

Title
Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds Michael-Andrei Panaitescu-Liess Yigitcan Kaya Sicheng Zhu Furong Huang Tudor Dumitras AAML 124 0 0 02 Apr 2025
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models Michael-Andrei Panaitescu-Liess Pankayaraj Pathmanathan Yigitcan Kaya Zora Che Bang An Sicheng Zhu Aakriti Agrawal Furong Huang AAML 118 2 0 10 Mar 2025
Mitigating Unauthorized Speech Synthesis for Voice Protection Zhisheng Zhang Qianyi Yang Derui Wang Pengyang Huang Yuxin Cao Kai Ye Jie Hao AAML 59 3 0 28 Oct 2024
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment Pankayaraj Pathmanathan Udari Madhushani Sehwag Michael-Andrei Panaitescu-Liess Furong Huang SILM AAML 116 0 0 15 Oct 2024
Clean Label Attacks against SLU Systems Lin Zhang Sonal Joshi Thomas Thebaud Jesus Villalba Najim Dehak Sanjeev Khudanpur AAML 61 0 0 13 Sep 2024
Vera Verto: Multimodal Hijacking Attack Minxing Zhang Wenhao Yang H. Bidkhori Yang Zhang AAML 43 0 0 31 Jul 2024
PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models Omead Brandon Pooladzandi Jeffrey Q. Jiang Sunay Bhat Gregory Pottie AAML 53 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 91 2 0 28 May 2024
FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models Yanting Wang Wei Zou Jinyuan Jia 90 1 0 12 Apr 2024
Have You Poisoned My Data? Defending Neural Networks against Data Poisoning Fabio De Gaspari Dorjan Hitaj Luigi V. Mancini AAML TDI 81 4 0 20 Mar 2024
Robust Influence-based Training Methods for Noisy Brain MRI Minh-Hao Van Alycia N. Carey Xintao Wu OOD NoLa 32 1 0 15 Mar 2024
SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models Yu Yang Siddhartha Mishra Jeffrey N Chiang Baharan Mirzasoleiman 98 24 0 12 Mar 2024
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models Yuancheng Xu Jiarui Yao Manli Shu Yanchao Sun Zichu Wu Ning Yu Tom Goldstein Furong Huang AAML 125 25 0 05 Feb 2024
A Comprehensive Survey of Attack Techniques, Implementation, and Mitigation Strategies in Large Language Models Aysan Esmradi Daniel Wankit Yip C. Chan AAML 83 14 0 18 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 101 42 0 14 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 116 4 0 08 Dec 2023
Mendata: A Framework to Purify Manipulated Training Data Zonghao Huang Neil Zhenqiang Gong Michael K. Reiter 59 0 0 03 Dec 2023
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective Sahil Verma Gantavya Bhatt Avi Schwarzschild Soumye Singhal Arnav M. Das Chirag Shah John P Dickerson Jeff Bilmes J. Bilmes AAML 96 1 0 25 Nov 2023
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks Minh-Hao Van Alycia N. Carey Xintao Wu TDI AAML 71 3 0 15 Sep 2023
Rethinking Backdoor Attacks Alaa Khaddaj Guillaume Leclerc Aleksandar Makelov Kristian Georgiev Hadi Salman Andrew Ilyas Aleksander Madry SILM 76 29 0 19 Jul 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 134 8 0 14 Jun 2023
CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning Hritik Bansal Nishad Singhi Yu Yang Fan Yin Aditya Grover Kai-Wei Chang AAML 109 46 0 06 Mar 2023
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks Jimmy Z. Di Jack Douglas Jayadev Acharya Gautam Kamath Ayush Sekhari MU 81 47 0 21 Dec 2022
Differentially Private Optimizers Can Learn Adversarially Robust Models Yuan Zhang Zhiqi Bu 83 3 0 16 Nov 2022
Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks Tianwei Liu Yu Yang Baharan Mirzasoleiman AAML 87 27 0 14 Aug 2022
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning Antonio Emanuele Cinà Kathrin Grosse Ambra Demontis Sebastiano Vascon Werner Zellinger Bernhard A. Moser Alina Oprea Battista Biggio Marcello Pelillo Fabio Roli AAML 93 127 0 04 May 2022