Weight Poisoning Attacks on Pre-trained Models

14 April 2020

Graham Neubig

Papers citing "Weight Poisoning Attacks on Pre-trained Models"

50 / 97 papers shown

Title
Threat Modeling for AI: The Case for an Asset-Centric Approach Jose Sanchez Vicarte Marcin Spoczynski Mostafa Elsaid 29 0 0 08 May 2025
Adversarial Attacks in Multimodal Systems: A Practitioner's Survey Shashank Kapoor Sanjay Surendranath Girija Lakshit Arora Dipen Pradhan Ankit Shetgaonkar Aman Raj AAML 77 0 0 06 May 2025
A Survey on Privacy Risks and Protection in Large Language Models Kang Chen Xiuze Zhou Yuanguo Lin Shibo Feng Li Shen Pengcheng Wu AILaw PILM 171 0 0 04 May 2025
Backdoor Attacks Against Patch-based Mixture of Experts Cedric Chan Jona te Lintelo S. Picek AAML MoE 172 0 0 03 May 2025
GaussTrap: Stealthy Poisoning Attacks on 3D Gaussian Splatting for Targeted Scene Confusion Jiaxin Hong Sixu Chen Shuoyang Sun Hongyao Yu Hao Fang Yuqi Tan Bin Chen Shuhan Qi Jiawei Li 3DGS AAML 153 0 0 29 Apr 2025
BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts Qingyue Wang Qi Pang Xixun Lin Shuai Wang Daoyuan Wu MoE 62 0 0 24 Apr 2025
The Ultimate Cookbook for Invisible Poison: Crafting Subtle Clean-Label Text Backdoors with Style Attributes Wencong You Daniel Lowd 39 0 0 24 Apr 2025
PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization Yang Jiao Xiao Wang Kai Yang AAML SILM 35 0 0 10 Apr 2025
Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain Yuanmin Huang Mi Zhang Zhaoxiang Wang Wenxuan Li Min Yang AAML AI4TS 59 0 0 12 Mar 2025
Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images Yubo Wang Jianting Tang Chaohu Liu Linli Xu AAML 63 1 0 23 Feb 2025
When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations Huaizhi Ge Yiming Li Qifan Wang Yongfeng Zhang Ruixiang Tang AAML SILM 86 0 0 19 Nov 2024
LLMScan: Causal Scan for LLM Misbehavior Detection Mengdi Zhang Kai Kiat Goh Peixin Zhang Jun Sun Rose Lin Xin Hongyu Zhang 25 0 0 22 Oct 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 36 1 0 03 Sep 2024
Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss Guang Yang Yu Zhou Xiang Chen Xiangyu Zhang Terry Yue Zhuo David Lo Taolue Chen AAML 57 4 0 12 Jul 2024
Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data Tim Baumgärtner Yang Gao Dana Alon Donald Metzler AAML 30 18 0 08 Apr 2024
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors Victoria Graf Qin Liu Muhao Chen AAML 37 8 0 02 Apr 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
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents Wenkai Yang Xiaohan Bi Yankai Lin Sishuo Chen Jie Zhou Xu Sun LLMAG AAML 44 53 0 17 Feb 2024
Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models Weijiao Zhang Jindong Han Zhao Xu Hang Ni Hao Liu Hui Xiong Hui Xiong AI4CE 77 15 0 30 Jan 2024
Punctuation Matters! Stealthy Backdoor Attack for Language Models Xuan Sheng Zhicheng Li Zhaoyang Han Xiangmao Chang Piji Li 40 3 0 26 Dec 2023
Universal Jailbreak Backdoors from Poisoned Human Feedback Javier Rando Florian Tramèr 23 60 0 24 Nov 2023
Efficient Trigger Word Insertion Yueqi Zeng Ziqiang Li Pengfei Xia Lei Liu Bin Li AAML 21 5 0 23 Nov 2023
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models Jiong Wang Junlin Wu Muhao Chen Yevgeniy Vorobeychik Chaowei Xiao AAML 29 12 0 16 Nov 2023
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations Wenjie Mo Lyne Tchapmi Qin Liu Jiong Wang Jun Yan Chaowei Xiao Muhao Chen Muhao Chen AAML 61 17 0 16 Nov 2023
Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models Yueqing Liang Lu Cheng Ali Payani Kai Shu 28 3 0 15 Nov 2023
Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots Ruixiang Tang Jiayi Yuan Yiming Li Zirui Liu Rui Chen Xia Hu AAML 36 13 0 28 Oct 2023
Everyone Can Attack: Repurpose Lossy Compression as a Natural Backdoor Attack Sze Jue Yang Q. Nguyen Chee Seng Chan Khoa D. Doan AAML DiffM 32 0 0 31 Aug 2023
Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems Ashim Gupta Amrith Krishna AAML 22 16 0 31 May 2023
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models Kai Mei Zheng Li Zhenting Wang Yang Zhang Shiqing Ma AAML SILM 37 48 0 28 May 2023
Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model Aoi Ito Shota Horiguchi SSL 27 2 0 24 May 2023
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE Qin Liu Fei Wang Chaowei Xiao Muhao Chen AAML 37 21 0 24 May 2023
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation Xuanli He Qiongkai Xu Jun Wang Benjamin I. P. Rubinstein Trevor Cohn AAML 32 18 0 19 May 2023
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation Xiaowei Huang Wenjie Ruan Wei Huang Gao Jin Yizhen Dong ... Sihao Wu Peipei Xu Dengyu Wu André Freitas Mustafa A. Mustafa ALM 45 82 0 19 May 2023
Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias Zhiyuan Zhang Deli Chen Hao Zhou Fandong Meng Jie Zhou Xu Sun 36 5 0 08 May 2023
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning Shengfang Zhai Yinpeng Dong Qingni Shen Shih-Chieh Pu Yuejian Fang Hang Su 32 71 0 07 May 2023
Backdoor Learning on Sequence to Sequence Models Lichang Chen Minhao Cheng Heng-Chiao Huang SILM 54 18 0 03 May 2023
UNICORN: A Unified Backdoor Trigger Inversion Framework Zhenting Wang Kai Mei Juan Zhai Shiqing Ma LLMSV 35 44 0 05 Apr 2023
An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry Wenxin Jiang Nicholas Synovic Matt Hyatt Taylor R. Schorlemmer R. Sethi Yung-Hsiang Lu George K. Thiruvathukal James C. Davis 30 64 0 05 Mar 2023
Backdoor Attacks to Pre-trained Unified Foundation Models Zenghui Yuan Yixin Liu Kai Zhang Pan Zhou Lichao Sun AAML 32 10 0 18 Feb 2023
Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions Marwan Omar SILM AAML 33 20 0 14 Feb 2023
Explainable AI does not provide the explanations end-users are asking for Savio Rozario G. Cevora XAI 20 0 0 25 Jan 2023
BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing Jiali Wei Ming Fan Wenjing Jiao Wuxia Jin Ting Liu AAML 29 10 0 25 Jan 2023
Circumventing interpretability: How to defeat mind-readers Lee D. Sharkey 35 3 0 21 Dec 2022
Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety Joshua Albrecht Ellie Kitanidis Abraham J. Fetterman ELM ReLM ALM LRM 27 17 0 13 Dec 2022
UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning Ziyao Wang Thai Le Dongwon Lee 36 1 0 17 Nov 2022
MSDT: Masked Language Model Scoring Defense in Text Domain Jaechul Roh Minhao Cheng Yajun Fang AAML 15 1 0 10 Nov 2022
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis Lukas Struppek Dominik Hintersdorf Kristian Kersting SILM 22 36 0 04 Nov 2022
Dormant Neural Trojans Feisi Fu Panagiota Kiourti Wenchao Li AAML 30 0 0 02 Nov 2022
Poison Attack and Defense on Deep Source Code Processing Models Jia Li Zhuo Li Huangzhao Zhang Ge Li Zhi Jin Xing Hu Xin Xia AAML 40 16 0 31 Oct 2022
Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning Xiaoyi Chen Baisong Xin Shengfang Zhai Shiqing Ma Qingni Shen Zhonghai Wu SILM 19 2 0 20 Oct 2022