SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models.

Muxi Diao Rumei Li Shiyang Liu Guogang Liao Jingang Wang Xunliang Cai Weiran Xu SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models. 23778-23786 2025 AAAI https://doi.org/10.1609/aaai.v39i22.34549 conf/aaai/2025 db/conf/aaai/aaai2025.html#DiaoLLLWCX25