A critical vulnerability has been disclosed in the Google Cloud Vertex AI SDK for Python that could allow attackers to hijack model uploads, inject malicious payloads, and achieve remote code execution (RCE) all without any initial access to a victim’s cloud project. The vulnerability was responsibly disclosed to Google, which has since released a patch […]
The post Google Cloud Vertex AI Flaw Enables Model Hijacking and Poisoning Attacks appeared first on Cyber Security News.