AINewsnow

Poisoned Training Artifacts Turn a Coding Agent Against Its Operator

TL;DR A post-training supply chain attack is a way to plant hidden behaviour in a model after its base training, inserted through the fine-tuning data or through the checkpoint that gets distributed. Microsoft's Defender Research and AI Red Team published two studies on 12 November 2026 that measur…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-15 14:00 · DEV Community — AI
    Poisoned Training Artifacts Turn a Coding Agent Against Its Operator

More stories

  1. Grounded flights, Microsoft outage and AI turmoil fuel fears of wider tech breakdown — Washington Post AI
  2. Microsoft 365 restored after day-long global outage affecting Outlook, Teams and Copilot — Data Center Dynamics
  3. Nvidia Fallout, Microsoft Outage and Anthropic's IPO Push — Bloomberg AI
  4. Cerebras signs Microsoft as cloud customer and raises 2026 forecast after Q3 beat — Data Center Dynamics
  5. Microsoft outage enters second day, disrupting businesses and Claude — Business Insider AI
  6. MIT unveils AI copilot that seeks human feedback for structural design — MIT News AI
  7. Major Microsoft outage disrupts Teams, Outlook and Copilot for thousands of users — The Independent Tech
  8. Microsoft Playwright Now Helps Ai Agents Run Browsers And Tests — DEV Community — Machine Learning

Get the daily brief of stories like this at 6:30 every morning →