CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
Authors: Qibing Ren, Chang Gao, Jing Shao, Junchi Yan, Xin Tan, Wai Lam, Lizhuang Ma | Published: 2024-03-12 | Updated: 2024-09-14
LLMセキュリティ
Fuzzing BusyBox: Leveraging LLM and Crash Reuse for Embedded Bug Unearthing
Authors: Asmita, Yaroslav Oliinyk, Michael Scott, Ryan Tsang, Chongzhou Fang, Houman Homayoun | Published: 2024-03-06
AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks
Authors: Jiacen Xu, Jack W. Stokes, Geoff McDonald, Xuesong Bai, David Marshall, Siyue Wang, Adith Swaminathan, Zhou Li | Published: 2024-03-02
Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
Authors: Tong Liu, Yingjie Zhang, Zhe Zhao, Yinpeng Dong, Guozhu Meng, Kai Chen | Published: 2024-02-28 | Updated: 2024-06-10
LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper
Authors: Daoyuan Wu, Shuai Wang, Yang Liu, Ning Liu | Published: 2024-02-24 | Updated: 2024-03-04
On Trojan Signatures in Large Language Models of Code
Authors: Aftab Hussain, Md Rafiqul Islam Rabin, Mohammad Amin Alipour | Published: 2024-02-23 | Updated: 2024-03-07
Coercing LLMs to do and reveal (almost) anything
Authors: Jonas Geiping, Alex Stein, Manli Shu, Khalid Saifullah, Yuxin Wen, Tom Goldstein | Published: 2024-02-21
A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
Authors: Zihao Xu, Yi Liu, Gelei Deng, Yuekang Li, Stjepan Picek | Published: 2024-02-21 | Updated: 2024-05-17
The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
Authors: Zhen Tan, Chengshuai Zhao, Raha Moraffah, Yifan Li, Yu Kong, Tianlong Chen, Huan Liu | Published: 2024-02-20 | Updated: 2024-06-03
TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification
Authors: Martin Gubri, Dennis Ulmer, Hwaran Lee, Sangdoo Yun, Seong Joon Oh | Published: 2024-02-20 | Updated: 2024-06-06