LIVE FEED
Post-Training Supply Chain Attacks Backdoor AI Coding Agents

Post-Training Supply Chain Attacks Backdoor AI Coding Agents

ATLAS OWASP CRITICAL Active exploitation · Immediate action required ▲ 9.2 Microsoft Security Blog

Microsoft Security Research and the AI Red Team have demonstrated two post-training supply chain attack vectors—dataset poisoning and model poisoning—that embed persistent backdoors in AI coding agents. Dataset poisoning achieved approximately 78% attack success by training models to discover and misuse any available command-execution tool when triggered by routine user requests. These findings underscore that enterprise AI deployments cannot rely on model-level evaluation alone and require external observability and controls.

NVIDIA and Hugging Face Launch GR00T 1.7 Robot Model

NVIDIA and Hugging Face Launch GR00T 1.7 Robot Model

FIRST LOOK ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 7.8 NVIDIA AI Blog

NVIDIA and Hugging Face have integrated the Isaac GR00T 1.7 vision-language-action model, Isaac Teleop framework, and a 350,000-trajectory open dataset into the LeRobot open-source robotics library, creating an end-to-end open pipeline for training and deploying physical AI systems. This dramatically lowers the barrier to fine-tuning and deploying robot foundation models, expanding the attack surface across the full ML supply chain — from poisoned community datasets to adversarially crafted demonstrations used in teleop data collection. Defenders responsible for robotics deployments must now contend with a large, loosely governed open-source ecosystem where compromised models or datasets can directly translate to unsafe physical-world behaviour.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.