Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models

29 March 2021

Lei Li

Xuancheng Ren

Papers citing "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models"

33 / 33 papers shown

Title
LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures Francisco Aguilera-Martínez Fernando Berzal PILM 57 0 0 02 May 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
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 64 0 0 24 Apr 2025
Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs Himanshu Beniwal Sailesh Panda Birudugadda Srivibhav Mayank Singh 45 0 0 24 Feb 2025
Is poisoning a real threat to LLM alignment? Maybe more so than you think Pankayaraj Pathmanathan Souradip Chakraborty Xiangyu Liu Yongyuan Liang Furong Huang AAML 52 14 0 17 Jun 2024
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors Victoria Graf Qin Liu Muhao Chen AAML 40 8 0 02 Apr 2024
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment Jiong Wang Jiazhao Li Yiquan Li Xiangyu Qi Junjie Hu Yixuan Li P. McDaniel Muhao Chen Bo Li Chaowei Xiao AAML SILM 40 18 0 22 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 48 56 0 17 Feb 2024
Manipulating Predictions over Discrete Inputs in Machine Teaching Xiaodong Wu Yufei Han H. Dahrouj Jianbing Ni Zhenwen Liang Xiangliang Zhang 23 0 0 31 Jan 2024
Punctuation Matters! Stealthy Backdoor Attack for Language Models Xuan Sheng Zhicheng Li Zhaoyang Han Xiangmao Chang Piji Li 43 3 0 26 Dec 2023
Universal Jailbreak Backdoors from Poisoned Human Feedback Javier Rando Florian Tramèr 26 63 0 24 Nov 2023
Efficient Trigger Word Insertion Yueqi Zeng Ziqiang Li Pengfei Xia Lei Liu Bin Li AAML 23 5 0 23 Nov 2023
A Comprehensive Overview of Backdoor Attacks in Large Language Models within Communication Networks Haomiao Yang Kunlan Xiang Mengyu Ge Hongwei Li Rongxing Lu Shui Yu SILM 30 41 0 28 Aug 2023
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE Qin Liu Fei Wang Chaowei Xiao Muhao Chen AAML 37 22 0 24 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 52 83 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
UNICORN: A Unified Backdoor Trigger Inversion Framework Zhenting Wang Kai Mei Juan Zhai Shiqing Ma LLMSV 39 44 0 05 Apr 2023
Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions Marwan Omar SILM AAML 37 20 0 14 Feb 2023
Stealthy Backdoor Attack for Code Models Zhou Yang Bowen Xu Jie M. Zhang Hong Jin Kang Jieke Shi Junda He David Lo AAML 26 65 0 06 Jan 2023
UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning Ziyao Wang Thai Le Dongwon Lee 36 1 0 17 Nov 2022
BadRes: Reveal the Backdoors through Residual Connection Min He Tianyu Chen Haoyi Zhou Shanghang Zhang Jianxin Li 24 0 0 15 Sep 2022
Catch Me If You Can: Deceiving Stance Detection and Geotagging Models to Protect Privacy of Individuals on Twitter Dilara Doğan Bahadir Altun Muhammed Said Zengin Mucahid Kutlu Tamer Elsayed 26 2 0 23 Jul 2022
Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling Kiyoon Yoo Nojun Kwak SILM AAML FedML 25 19 0 29 Apr 2022
Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense Guangyu Shen Yingqi Liu Guanhong Tao Qiuling Xu Zhuo Zhang Shengwei An Shiqing Ma Xinming Zhang AAML 23 34 0 11 Feb 2022
Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures Eugene Bagdasaryan Vitaly Shmatikov SILM AAML 33 78 0 09 Dec 2021
A General Framework for Defending Against Backdoor Attacks via Influence Graph Xiaofei Sun Jiwei Li Xiaoya Li Ziyao Wang Tianwei Zhang Han Qiu Fei Wu Chun Fan AAML TDI 24 5 0 29 Nov 2021
Triggerless Backdoor Attack for NLP Tasks with Clean Labels Leilei Gan Jiwei Li Tianwei Zhang Xiaoya Li Yuxian Meng Fei Wu Yi Yang Shangwei Guo Chun Fan AAML SILM 27 74 0 15 Nov 2021
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models Wenkai Yang Yankai Lin Peng Li Jie Zhou Xu Sun SILM AAML 34 103 0 15 Oct 2021
BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models Kangjie Chen Yuxian Meng Xiaofei Sun Shangwei Guo Tianwei Zhang Jiwei Li Chun Fan SILM 34 106 0 06 Oct 2021
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data Zhiyuan Zhang Lingjuan Lyu Weiqiang Wang Lichao Sun Xu Sun 21 35 0 03 Sep 2021
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning Linyang Li Demin Song Xiaonan Li Jiehang Zeng Ruotian Ma Xipeng Qiu 33 135 0 31 Aug 2021
Defending Against Backdoor Attacks in Natural Language Generation Xiaofei Sun Xiaoya Li Yuxian Meng Xiang Ao Fei Wu Jiwei Li Tianwei Zhang AAML SILM 31 47 0 03 Jun 2021
Backdoor Learning: A Survey Yiming Li Yong Jiang Zhifeng Li Shutao Xia AAML 45 592 0 17 Jul 2020