Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents
Kumar, Priyanshu, Lau, Elaine, Vijayakumar, Saranya, Trinh, Tu, Team, Scale Red, Chang, Elaine, Robinson, Vaughn, Hendryx, Sean, Zhou, Shuyan, Fredrikson, Matt, Yue, Summer, Wang, Zifan
Year of Publication 11.10.2024
Year of Publication 11.10.2024
Get full text
Journal Article
Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents
Kumar, Priyanshu, Lau, Elaine, Vijayakumar, Saranya, Tu Trinh, Scale Red Team, Chang, Elaine, Robinson, Vaughn, Hendryx, Sean, Zhou, Shuyan, Fredrikson, Matt, Yue, Summer, Wang, Zifan
Published in arXiv.org (11.10.2024)
Get full text
Published in arXiv.org (11.10.2024)
Paper