[Stanley]

Microsoft Develops Scanner to Detect Backdoors in Open-Weight Large Language Models

Microsoft on Wednesday said it built a lightweight scanner that it said can detect backdoors in open-weight large language models (LLMs) and improve the overall trust in artificial intelligence (AI) systems.
The tech giant's AI Security team said the scanner leverages three observable signals that can be used to reliably flag the presence of backdoors while maintaining a low false positive

https://thehackernews.com/2026/02/micros...etect.html

[shakur123]

Good initiative, but it also feels reactive.
Backdoors in open-weight models aren’t a new concern, so building a “lightweight scanner” now raises questions about how many compromised models may already be circulating