Diao M, Li R, Liu S, Liao G, Wang J, Cai X, et al. SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 19];39(22):23778-86. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/34549