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
- Changing fewer than 10 dormant neurons is enough to plant the backdoor, and no retraining is needed.
- The model passes standard safety tests, so the backdoor is hard to detect.
- A trigger can be as simple as a date change.
- Once triggered, the agent downloads and runs attacker code with the access it was given.
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
បន្ថែមពីវិស័យនេះ
- Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST - Walter Writes AI Tool Rewrites AI Text to Sound More Human, Ad Test Shows
This short video is a sponsored ad for Walter Writes AI, a tool that rewrites AI-generated text so it reads more like a person wrote it. The creator says they ran a paragraph through its detector, rewrote the flagged parts, and compared the scores before and after.
TheAIGRID · Nov 21, 06:15 KST - Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST