Trained to betray: How post-training supply chain attacks hijack coding agents
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. The post Trained to betray: How post-training supply chain attacks hijack coding agents appeared first on Microsoft Security Blog.
Malware & Threats
Vulnerabilities & Zero-Day
AI Security
Supply Chain Security
Threat Intelligence
Open Source
Incident Response & Forensics
Penetration Testing
Identity & Access Security
This page shows only the headline and the short summary. The full text is published by the original source.