新的进化框架揭示大语言模型安全漏洞

报道来源 [3]

1. arXiv cs.AI TIER_1 English(EN) · Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla · 2026-06-04 04:00

   TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

   arXiv:2602.06911v2 Announce Type: replace-cross Abstract: As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks. However,…

2. arXiv cs.CL TIER_1 English(EN) · Subhadip Mitra · 2026-06-02 04:00

   Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

   arXiv:2606.00801v1 Announce Type: cross 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 introdu…

3. arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Subhadip Mitra · 2026-05-30 16:40

   用于发现LLM安全领域多样化漏洞的质量-多样性进化

   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…