LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks
Authors: Qingzhao Zhang, Ziyang Xiong, Z. Morley Mao | Published: 2024-10-03 | Updated: 2025-04-09
Prompt Injection
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Authors: Hanrong Zhang, Jingyuan Huang, Kai Mei, Yifei Yao, Zhenting Wang, Chenlu Zhan, Hongwei Wang, Yongfeng Zhang | Published: 2024-10-03 | Updated: 2025-04-16
Optimizing Adaptive Attacks against Watermarks for Language Models
Authors: Abdulrahman Diaa, Toluwani Aremu, Nils Lukas | Published: 2024-10-03 | Updated: 2025-05-21
Robust LLM safeguarding via refusal feature adversarial training
Authors: Lei Yu, Virginie Do, Karen Hambardzumyan, Nicola Cancedda | Published: 2024-09-30 | Updated: 2025-03-20
System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective
Authors: Fangzhou Wu, Ethan Cecchetti, Chaowei Xiao | Published: 2024-09-27 | Updated: 2024-10-10
An Adversarial Perspective on Machine Unlearning for AI Safety
Authors: Jakub Łucki, Boyi Wei, Yangsibo Huang, Peter Henderson, Florian Tramèr, Javier Rando | Published: 2024-09-26 | Updated: 2025-04-10
Weak-to-Strong Backdoor Attack for Large Language Models
Authors: Shuai Zhao, Leilei Gan, Zhongliang Guo, Xiaobao Wu, Luwei Xiao, Xiaoyu Xu, Cong-Duy Nguyen, Luu Anh Tuan | Published: 2024-09-26 | Updated: 2024-10-13
MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks
Authors: Giandomenico Cornacchia, Giulio Zizzo, Kieran Fraser, Muhammad Zaid Hameed, Ambrish Rawat, Mark Purcell | Published: 2024-09-26 | Updated: 2024-10-04
PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach
Authors: Zhihao Lin, Wei Ma, Mingyi Zhou, Yanjie Zhao, Haoyu Wang, Yang Liu, Jun Wang, Li Li | Published: 2024-09-21 | Updated: 2024-10-03
LLM Honeypot: Leveraging Large Language Models as Advanced Interactive Honeypot Systems
Authors: Hakan T. Otal, M. Abdullah Canbaz | Published: 2024-09-12 | Updated: 2024-09-15