Google's Vertex AI Is Over-Privileged. That's a Problem
Palo Alto Networks researchers have identified over-privilege vulnerabilities in Google's Vertex AI platform, demonstrating how malicious actors could exploit AI agents to exfiltrate sensitive data …
AML.T0051 - LLM Prompt Injection
AML.T0057 - LLM Data Leakage
AML.T0040 - ML Model Inference API Access