Daren Zheng, Boning Zhang, and Julie Geibel. “VerifySafe: Toxicity-Safe Agent Responses under Adversarial Prompts With Evidence-Based Self-Verification”. Journal of Advanced Computing Systems 4, no. 1 (January 18, 2024): 67–82. Accessed March 5, 2026. https://scipublication.com/index.php/JACS/article/view/317.