⚡Megatron LLM Hub
←Back to search
Twitter

提出 Guardrail-based Vulnerability Discovery,绕开模型拒答自动挖洞

给出模型拒绝配合时仍能自动化漏洞发现的可操作思路,与 agent 安全直接相关
llmai_agent漏洞挖掘报告
RT @yo_yo_yo_jbo: Were you ever frustrated with your AI model for refusing finding vulnerabilities for you? What if I told you that you could still use it to find vulnerabilities, automatically? Welcome to Guardrail-based Vulnerability Discovery (GbVD)! https://t.co/B2cbCOJP6f