TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

22 May 2024

Papers citing "TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models"

6 / 6 papers shown

Title
Hoist with His Own Petard: Inducing Guardrails to Facilitate Denial-of-Service Attacks on Retrieval-Augmented Generation of LLMs Pan Suo Yu-ming Shang San-Chuan Guo Xi Zhang SILM AAML 45 0 0 30 Apr 2025
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 49 47 0 20 Mar 2024
PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models Hongwei Yao Jian Lou Zhan Qin SILM AAML 49 30 0 19 Oct 2023
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models Shuai Zhao Jinming Wen Anh Tuan Luu J. Zhao Jie Fu SILM 57 88 0 02 May 2023
BBQ: A Hand-Built Bias Benchmark for Question Answering Alicia Parrish Angelica Chen Nikita Nangia Vishakh Padmakumar Jason Phang Jana Thompson Phu Mon Htut Sam Bowman 212 364 0 15 Oct 2021
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models Nandan Thakur Nils Reimers Andreas Rucklé Abhishek Srivastava Iryna Gurevych VLM 229 961 0 17 Apr 2021