Primary
Attacker Diversity Reduction in Adaptive LLM Red Teaming
Primary source. Published by the vendor, CERT, regulator, government agency or researcher responsible.
arXiv:2611.19680v1 Announce Type: new Abstract: Reinforcement learning can make automated red-teaming more successful while narrowing the attacks it produces. Co-training an attacker and a defender with group-relative policy optimization (GRPO) has been reported to reduce attacker diversity. This experiment reproduces attack diversity reduction using three runs with a Qwen2.5-14B attacker and aโฆ
Read the full story at arXiv cs.CR (Cryptography & Security) โHackerNews24 shows a short summary only. The full article, its copyright and any corrections belong to the original publisher.