Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection

arXiv:2605. 24834v1 Announce Type: new Abstract: Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios, fictional framing, and indirect requests.