GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms
Authors: Sinan He, An Wang | Published: 2025-04-17
Prompt Injection
The Digital Cybersecurity Expert: How Far Have We Come?
Authors: Dawei Wang, Geng Zhou, Xianglong Li, Yu Bai, Li Chen, Ting Qin, Jian Sun, Dan Li | Published: 2025-04-16
Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails
Authors: William Hackett, Lewis Birch, Stefan Trawicki, Neeraj Suri, Peter Garraghan | Published: 2025-04-15 | Updated: 2025-04-16
Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
Authors: Yanbo Wang, Jiyang Guan, Jian Liang, Ran He | Published: 2025-04-14
An Investigation of Large Language Models and Their Vulnerabilities in Spam Detection
Authors: Qiyao Tang, Xiangyang Li | Published: 2025-04-14
CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
Authors: Liang-bo Ning, Shijie Wang, Wenqi Fan, Qing Li, Xin Xu, Hao Chen, Feiran Huang | Published: 2025-04-13 | Updated: 2025-04-24
Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking
Authors: Yu-Hang Wu, Yu-Jie Xiong, Jie-Zhang | Published: 2025-04-08
Generative Large Language Model usage in Smart Contract Vulnerability Detection
Authors: Peter Ince, Jiangshan Yu, Joseph K. Liu, Xiaoning Du | Published: 2025-04-07
Representation Bending for Large Language Model Safety
Authors: Ashkan Yousefpour, Taeheon Kim, Ryan S. Kwon, Seungbeen Lee, Wonje Jeung, Seungju Han, Alvin Wan, Harrison Ngan, Youngjae Yu, Jonghyun Choi | Published: 2025-04-02
LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution
Authors: Zhuoran Yang, Jie Peng, Zhen Tan, Tianlong Chen, Yanyong Zhang | Published: 2025-04-02