← Back to latest intelligence

Trained to betray: How post-training supply chain attacks hijack coding agents

Editorial abstract

Microsoft Defender Research and the AI Red Team discuss how poisoned datasets and poisoned model checkpoints can trigger remote code execution and other malicious activities.

This is not the publisher’s original article. Unreviewed abstracts are mechanically condensed from source-provided material; editor-reviewed abstracts have completed editorial review.

Story classification

Topics

US–China Competition and Supply-Chain Security · High confidence · AutomaticStory-text match

Regions

Global · Low confidence · AutomaticBroad source default; editorial correction recommended

Read original at Microsoft Security Blog ↗