⚡Megatron LLM Hub
←返回搜索
Twitter

开源项目 BLA 以投毒、耗竭、幻觉三步干扰 AI 逆向 Agent 的二进制分析

首批针对 LLM 逆向 Agent 的对抗工具,可自托管验证对抗效果
ai_agentllm工具对抗
BLA (Blind LLM Agents) - Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison ➡️ Exhaust ➡️ Hallucinate https://t.co/yYridbwOvp