Chimera: Compositional Jailbreak Attacks on LLMs via Judgment-Driven Search over Heterogeneous Strategies

Leo Hyun Park, Juwon Cho, Gyuhwan Kim, YoonDong Yeo, Taekyoung Kwon


Abstract
Large Language Models (LLMs) remain vulnerable to jailbreak attacks despite extensive safety alignment. While automated red-teaming has emerged as a critical evaluation protocol, existing methods face two primary limitations: they largely explore homogeneous transformations in isolation, and they rely on brittle judgment metrics that frequently misclassify non-refusal hallucinations as successful attacks. In this paper, we reformulate jailbreak attacks as a compositional search problem guided by context-aware evaluation. We propose Chimera, a framework that generates compositional jailbreak attacks via judgment-driven search over heterogeneous strategies. Chimera systematically explores the combinatorial space of disjoint primitives, such as integrating technical obfuscation with semantic persuasion, under strict ordering constraints. Crucially, to drive the search process effectively, we introduce StrongREJECT++, a relevance-aware metric that eliminates false positive rewards by penalizing irrelevant responses. Experiments on multiple open-source and commercial LLMs show that Chimera uncovers qualitatively different vulnerability regions and consistently improves attack success rates and transferability compared to state-of-the-art baselines.
Anthology ID:
2026.findings-acl.1667
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
33330–33355
Language:
URL:
https://aclanthology.org/2026.findings-acl.1667/
DOI:
10.18653/v1/2026.findings-acl.1667
Bibkey:
Cite (ACL):
Leo Hyun Park, Juwon Cho, Gyuhwan Kim, YoonDong Yeo, and Taekyoung Kwon. 2026. Chimera: Compositional Jailbreak Attacks on LLMs via Judgment-Driven Search over Heterogeneous Strategies. In Findings of the Association for Computational Linguistics: ACL 2026, pages 33330–33355, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Chimera: Compositional Jailbreak Attacks on LLMs via Judgment-Driven Search over Heterogeneous Strategies (Park et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.1667.pdf
Checklist:
 2026.findings-acl.1667.checklist.pdf