ត្រឡប់ទៅព័ត៌មានវិញ

AI · ផ្លូវការ

Microsoft Researchers Reveal 'Lazarus' Backdoor That Hides Malicious Commands in Dormant AI Neurons

Microsoft Research blog ·

មើលត្រួសៗ

Microsoft researchers found a backdoor technique called Lazarus that reprograms a few dormant neurons in an AI model. The model behaves normally until a hidden trigger appears, then runs malicious commands. The risk is highest for AI agents that have access to tools or terminals.

ចំណុចសំខាន់ៗ

ហេតុអ្វីវាសំខាន់

As AI agents gain access to files and systems, checking where a model came from and confirming it has not been altered is becoming a core security task.

ប្រភពដើម

Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents

Microsoft Research blog · Nov 11, 05:52 KST

Read on Microsoft Research blog ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to Microsoft Research blog.

ការផ្សាយផ្សេងទៀត

AI