How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data

3 September 2021

Lichao Sun

Papers citing "How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data"

24 / 24 papers shown

Title
BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models Zenghui Yuan Jiawen Shi Pan Zhou Neil Zhenqiang Gong Lichao Sun AAML 66 1 0 20 Mar 2025
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing Keltin Grimes Marco Christiani David Shriver Marissa Connor KELM 80 1 0 17 Dec 2024
Revocable Backdoor for Deep Model Trading Yiran Xu Nan Zhong Zhenxing Qian Xinpeng Zhang AAML 27 0 0 01 Aug 2024
Flatness-aware Sequential Learning Generates Resilient Backdoors Hoang Pham The-Anh Ta Anh Tran Khoa D. Doan FedML AAML 31 0 0 20 Jul 2024
BadEdit: Backdooring large language models by model editing Yanzhou Li Tianlin Li Kangjie Chen Jian Zhang Shangqing Liu Wenhan Wang Tianwei Zhang Yang Liu SyDa AAML KELM 54 50 0 20 Mar 2024
Test-Time Backdoor Attacks on Multimodal Large Language Models Dong Lu Tianyu Pang Chao Du Qian Liu Xianjun Yang Min-Bin Lin AAML 51 21 0 13 Feb 2024
Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs Xuandong Zhao Lei Li Yu-Xiang Wang 55 12 0 08 Feb 2024
Label Poisoning is All You Need Rishi Jha J. Hayase Sewoong Oh AAML 22 28 0 29 Oct 2023
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data Lukas Struppek Martin Hentschel Clifton A. Poth Dominik Hintersdorf Kristian Kersting SILM DiffM 12 4 0 10 Oct 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 26 5 0 08 May 2023
Backdoor Attacks with Input-unique Triggers in NLP Xukun Zhou Jiwei Li Tianwei Zhang Lingjuan Lyu Muqiao Yang Jun He SILM AAML 14 9 0 25 Mar 2023
Black-box Backdoor Defense via Zero-shot Image Purification Yucheng Shi Mengnan Du Xuansheng Wu Zihan Guan Jin Sun Ninghao Liu 32 26 0 21 Mar 2023
Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective Baoyuan Wu Zihao Zhu Li Liu Qingshan Liu Zhaofeng He Siwei Lyu AAML 44 21 0 19 Feb 2023
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models Zhiyuan Zhang Lingjuan Lyu Xingjun Ma Chenguang Wang Xu Sun AAML 23 41 0 18 Oct 2022
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks Sishuo Chen Wenkai Yang Zhiyuan Zhang Xiaohan Bi Xu Sun SILM AAML 24 23 0 14 Oct 2022
Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation Zhiyuan Zhang Qi Su Xu Sun FedML 15 12 0 13 Oct 2022
Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork Haotao Wang Junyuan Hong Aston Zhang Jiayu Zhou Zhangyang Wang AAML 28 12 0 12 Oct 2022
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks Xuanli He Qiongkai Xu Yi Zeng Lingjuan Lyu Fangzhao Wu Jiwei Li R. Jia WaLM 177 71 0 19 Sep 2022
Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons Mingyuan Fan Yang Liu Cen Chen Ximeng Liu Wenzhong Guo AAML 11 4 0 13 Aug 2022
Black-box Dataset Ownership Verification via Backdoor Watermarking Yiming Li Mingyan Zhu Xue Yang Yong Jiang Tao Wei Shutao Xia AAML 24 73 0 04 Aug 2022
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation Tong Wu Tianhao Wang Vikash Sehwag Saeed Mahloujifar Prateek Mittal AAML 27 36 0 22 Jul 2022
Backdoor Attacks on Crowd Counting Yuhua Sun Tailai Zhang Xingjun Ma Pan Zhou Jian Lou Zichuan Xu Xing Di Yu Cheng Lichao AAML 11 15 0 12 Jul 2022
Backdoor Learning: A Survey Yiming Li Yong Jiang Zhifeng Li Shutao Xia AAML 35 585 0 17 Jul 2020
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 273 2,878 0 15 Sep 2016