BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards
Authors: Diego Dorn, Alexandre Variengien, Charbel-Raphaël Segerie, Vincent Corruble | Published: 2024-06-03
Prompt Injection
Exploring Vulnerabilities and Protections in Large Language Models: A Survey
Authors: Frank Weizhen Liu, Chenhui Hu | Published: 2024-06-01
Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
Authors: Xiaojun Jia, Tianyu Pang, Chao Du, Yihao Huang, Jindong Gu, Yang Liu, Xiaochun Cao, Min Lin | Published: 2024-05-31 | Updated: 2024-06-05
Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
Authors: Chen Xiong, Xiangyu Qi, Pin-Yu Chen, Tsung-Yi Ho | Published: 2024-05-30 | Updated: 2025-06-04
Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems
Authors: Ruochen Jiao, Shaoyuan Xie, Justin Yue, Takami Sato, Lixu Wang, Yixuan Wang, Qi Alfred Chen, Qi Zhu | Published: 2024-05-27 | Updated: 2025-04-30
Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
Authors: Xijie Huang, Xinyuan Wang, Hantao Zhang, Yinghao Zhu, Jiawen Xi, Jingkun An, Hao Wang, Hao Liang, Chengwei Pan | Published: 2024-05-26 | Updated: 2024-08-21
Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character
Authors: Siyuan Ma, Weidi Luo, Yu Wang, Xiaogeng Liu | Published: 2024-05-25 | Updated: 2024-06-12
Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study
Authors: Karl Tamberg, Hayretdin Bahsi | Published: 2024-05-24
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
Authors: Guanlin Li, Kangjie Chen, Shudong Zhang, Jie Zhang, Tianwei Zhang | Published: 2024-05-24 | Updated: 2024-10-11
Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
Authors: Yu Fu, Wen Xiao, Jia Chen, Jiachen Li, Evangelos Papalexakis, Aichi Chien, Yue Dong | Published: 2024-05-24