作者位次 #5/9ACL 2026Poster· Natural Language Processing
Jailbreak-Zero: A Path to P areto Optimal Red Teaming for Large Language Models
Kai Hu · Abhinav Aggarwal · Mehran Khodabandeh · David Zhang · Eric Hsin · Li Chen · Ankit Jain · Matt Fredrikson · Akash Bharadwaj
摘要
This paper presents a novel Automated Red Teaming (ART) framework that shifts from example-based to policy-based evaluation, addressing critical limitations in scalability and validity. We define harmful content through abstract safety policies rather than specific static examples. We also introd...