SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits 事件

SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits arXiv:2604.01473v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious queries, which either introduce substantial latency or suffer from randomness in text generation. To overcome these limitations, we propo