ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

20 November 2020

Maosong Sun

Papers citing "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"

50 / 164 papers shown

Title
Securing Multi-turn Conversational Language Models Against Distributed Backdoor Triggers Terry Tong Jiashu Xu Qin Liu Muhao Chen AAML SILM 37 1 0 04 Jul 2024
SOS! Soft Prompt Attack Against Open-Source Large Language Models Ziqing Yang Michael Backes Yang Zhang Ahmed Salem AAML 38 6 0 03 Jul 2024
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models Yi Zeng Weiyu Sun Tran Ngoc Huynh Dawn Song Bo Li Ruoxi Jia AAML LLMSV 35 17 0 24 Jun 2024
Attack and Defense of Deep Learning Models in the Field of Web Attack Detection Lijia Shi Shihao Dong AAML 25 0 0 18 Jun 2024
FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation Bangzheng Li Ben Zhou Xingyu Fu Fei Wang Dan Roth Muhao Chen 26 3 0 17 Jun 2024
Unique Security and Privacy Threats of Large Language Model: A Comprehensive Survey Shang Wang Tianqing Zhu Bo Liu Ming Ding Xu Guo Dayong Ye Wanlei Zhou Philip S. Yu PILM 57 17 0 12 Jun 2024
Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models Xi Li Yusen Zhang Renze Lou Chen Wu Jiaqi Wang LRM AAML 37 11 0 10 Jun 2024
Stealthy Targeted Backdoor Attacks against Image Captioning Wenshu Fan Hongwei Li Wenbo Jiang Meng Hao Shui Yu Xiao Zhang DiffM 22 6 0 09 Jun 2024
PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning Tianrong Zhang Zhaohan Xi Ting Wang Prasenjit Mitra Jinghui Chen AAML SILM 27 2 0 06 Jun 2024
Exploring Vulnerabilities and Protections in Large Language Models: A Survey Frank Weizhen Liu Chenhui Hu AAML 37 7 0 01 Jun 2024
TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models Yuzhou Nie Yanting Wang Jinyuan Jia Michael J. De Lucia Nathaniel D. Bastian Wenbo Guo Dawn Song SILM AAML 34 5 0 27 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 35 4 0 19 May 2024
BadActs: A Universal Backdoor Defense in the Activation Space Biao Yi Sishuo Chen Yiming Li Tong Li Baolei Zhang Zheli Liu AAML 33 5 0 18 May 2024
Taxonomy and Analysis of Sensitive User Queries in Generative AI Search Hwiyeol Jo Taiwoo Park Nayoung Choi Changbong Kim Ohjoon Kwon ... Kyoungho Shin Sun Suk Lim Kyungmi Kim Jihye Lee Sun Kim 60 0 0 05 Apr 2024
Exploring Backdoor Vulnerabilities of Chat Models Yunzhuo Hao Wenkai Yang Yankai Lin SILM KELM 21 9 0 03 Apr 2024
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors Victoria Graf Qin Liu Muhao Chen AAML 27 8 0 02 Apr 2024
Task-Agnostic Detector for Insertion-Based Backdoor Attacks Weimin Lyu Xiao Lin Songzhu Zheng Lu Pang Haibin Ling Susmit Jha Chao Chen 43 25 0 25 Mar 2024
$$\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models$ $\textit{LinkPrompt}$ : Natural and Universal Adversarial Attacks on Prompt-based Language Models Yue Xu Wenjie Wang SILM AAML 26 2 0 25 Mar 2024
Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices Sara Abdali Richard Anarfi C. Barberan Jia He PILM 65 24 0 19 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 56 12 0 29 Feb 2024
On Trojan Signatures in Large Language Models of Code Aftab Hussain Md Rafiqul Islam Rabin Mohammad Amin Alipour 41 2 0 23 Feb 2024
Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs Xiaoxia Li Siyuan Liang Jiyi Zhang Hansheng Fang Aishan Liu Ee-Chien Chang 90 24 0 21 Feb 2024
Learning to Poison Large Language Models During Instruction Tuning Yao Qiang Xiangyu Zhou Saleh Zare Zade Mohammad Amin Roshani Douglas Zytko Dongxiao Zhu AAML SILM 32 20 0 21 Feb 2024
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning Shuai Zhao Leilei Gan Anh Tuan Luu Jie Fu Lingjuan Lyu Meihuizi Jia Jinming Wen AAML 21 22 0 19 Feb 2024
Purifying Large Language Models by Ensembling a Small Language Model Tianlin Li Qian Liu Tianyu Pang Chao Du Qing-Wu Guo Yang Liu Min-Bin Lin 46 16 0 19 Feb 2024
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space Zongru Wu Zhuosheng Zhang Pengzhou Cheng Gongshen Liu AAML 39 4 0 19 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
OrderBkd: Textual backdoor attack through repositioning Irina Alekseevskaia Konstantin Arkhipenko 17 2 0 12 Feb 2024
Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers Lei Xu Sarah Alnegheimish Laure Berti-Equille Alfredo Cuesta-Infante K. Veeramachaneni AAML 19 0 0 30 Jan 2024
Security and Privacy Challenges of Large Language Models: A Survey B. Das M. H. Amini Yanzhao Wu PILM ELM 19 101 0 30 Jan 2024
Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning Shuai Zhao Meihuizi Jia Anh Tuan Luu Fengjun Pan Jinming Wen AAML 29 35 0 11 Jan 2024
A Comprehensive Survey of Attack Techniques, Implementation, and Mitigation Strategies in Large Language Models Aysan Esmradi Daniel Wankit Yip C. Chan AAML 30 11 0 18 Dec 2023
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning Meng Zheng Jiaqi Xue Xun Chen YanShan Wang Qian Lou Lei Jiang AAML 23 7 0 16 Dec 2023
A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly Yifan Yao Jinhao Duan Kaidi Xu Yuanfang Cai Eric Sun Yue Zhang PILM ELM 29 473 0 04 Dec 2023
Grounding Foundation Models through Federated Transfer Learning: A General Framework Yan Kang Tao Fan Hanlin Gu Xiaojin Zhang Lixin Fan Qiang Yang AI4CE 68 19 0 29 Nov 2023
TextGuard: Provable Defense against Backdoor Attacks on Text Classification Hengzhi Pei Jinyuan Jia Wenbo Guo Bo-wen Li Dawn Song SILM 21 9 0 19 Nov 2023
Hijacking Large Language Models via Adversarial In-Context Learning Yao Qiang Xiangyu Zhou Dongxiao Zhu 30 32 0 16 Nov 2023
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations Wenjie Mo Jiashu Xu Qin Liu Jiong Wang Jun Yan Chaowei Xiao Muhao Chen Muhao Chen AAML 54 17 0 16 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 31 13 0 28 Oct 2023
Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers Wencong You Zayd Hammoudeh Daniel Lowd AAML 11 12 0 28 Oct 2023
Attention-Enhancing Backdoor Attacks Against BERT-based Models Weimin Lyu Songzhu Zheng Lu Pang Haibin Ling Chao Chen 21 34 0 23 Oct 2023
Privacy in Large Language Models: Attacks, Defenses and Future Directions Haoran Li Yulin Chen Jinglong Luo Yan Kang Xiaojin Zhang Qi Hu Chunkit Chan Yangqiu Song PILM 38 41 0 16 Oct 2023
Composite Backdoor Attacks Against Large Language Models Hai Huang Zhengyu Zhao Michael Backes Yun Shen Yang Zhang AAML 17 36 0 11 Oct 2023
The Trickle-down Impact of Reward (In-)consistency on RLHF Lingfeng Shen Sihao Chen Linfeng Song Lifeng Jin Baolin Peng Haitao Mi Daniel Khashabi Dong Yu 18 21 0 28 Sep 2023
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks Zhaohan Xi Tianyu Du Changjiang Li Ren Pang S. Ji Jinghui Chen Fenglong Ma Ting Wang AAML 8 29 0 23 Sep 2023
Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review Pengzhou Cheng Zongru Wu Wei Du Haodong Zhao Wei Lu Gongshen Liu SILM AAML 18 17 0 12 Sep 2023
LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors Chengkun Wei Wenlong Meng Zhikun Zhang M. Chen Ming-Hui Zhao Wenjing Fang Lei Wang Zihui Zhang Wenzhi Chen AAML 13 8 0 26 Aug 2023
Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities Maximilian Mozes Xuanli He Bennett Kleinberg Lewis D. Griffin 31 76 0 24 Aug 2023
TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models Indranil Sur Karan Sikka Matthew Walmer K. Koneripalli Anirban Roy Xiaoyu Lin Ajay Divakaran Susmit Jha 24 8 0 07 Aug 2023
ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP Lu Yan Zhuo Zhang Guanhong Tao Kaiyuan Zhang Xuan Chen Guangyu Shen Xiangyu Zhang AAML SILM 54 16 0 04 Aug 2023