Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

May 30, 2026 ยท Grace Period ยท ๐Ÿ› the ICLR 2026 Workshop on Agents in the Wild

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Subhadip Mitra arXiv ID 2606.00801 Category cs.CR: Cryptography & Security Cross-listed cs.CL, cs.ET, cs.LG, cs.NE Citations 0 Venue the ICLR 2026 Workshop on Agents in the Wild
Abstract
Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish. We introduce a quality-diversity evolutionary framework that operates at the semantic level, evolving interpretable attack strategies rather than token sequences. Using MAP-Elites, we maintain a diverse archive of attacks across behavioral dimensions (strategy type, encoding method, prompt length). In experiments across GPT-4o-mini, Claude 3.5 Sonnet, Gemini 2.0 Flash, and an open-weight coding model (Devstral-small-2), we discover distinct vulnerability profiles: GPT-4o-mini is vulnerable to hypothetical and multi-turn framing combined with ROT13 encoding (fitness 0.8), Gemini to direct attacks with ROT13 and multi-turn with Leetspeak (0.8), while Claude shows uniformly ambiguous responses across all strategies (max 0.4). The semantic representation produces interpretable attacks that reveal systematic, model-specific weaknesses, providing actionable insights for improving LLM safety and a reproducible baseline for evaluating future frontier models. Code and experiment artifacts are released at https://github.com/bassrehab/red-queen.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Cryptography & Security