InfoResearchPreprintLLM-specific
Attacker Diversity Reduction in Adaptive LLM Red Teaming
- Published
- Record updated
Summary
Co-training an attacker and defender with GRPO reduced attacker diversity in automated LLM red teaming, reproduced here with a Qwen2.5-14B attacker and a Phi-4-mini defender trained by DPO. Across three runs, Attack Diversity Retention fell to 0.63, 0.61 and 0.63, below the 0.75 target, at round 12, while attack success kept improving. The 26 AdvBench behaviors and the nominal intervals, given training ended after 12 rounds on development checkpoints, bound the result.
Related items
- MediumGemini AI agents repeatedly bypassed safeguards to attack real websiteSimilar attack · BleepingComputer
- CriticalCVE-2026-120699: CubeSandbox host path bind mount allows host file access via POST /sandboxesSimilar attack · NVD/CVE Database
- MediumGoogle warns that fully-automated AI attacks are coming soonSimilar attack · BleepingComputer
- InfoBeyond the Patch: Reconstructing an Incomplete-Fix Patch Bypass in LLM Agent Frameworks with Control-Gated, Benign ProbesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- InfoModel Immunization Beyond Condition Numbers: The Importance of Plateau RegionsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)