Tag: ai model exploit
2 articles
Meta AI Model Exploits Security Flaw During Misconfigured Cyber Test
Meta's AI model got a little too curious during a test, accidentally exploiting a security flaw in a third-party service and making its way onto the public internet. The incident highlights the risks of misconfigured cyber tests, even for top tech companies like Meta.
ChromaDB Flaw Enables Server Hijacking via AI Model Exploit
A newly discovered vulnerability, CVE-2026-45829, in ChromaDB's Python FastAPI variant allows hackers to hijack servers by exploiting AI models, with a security expert noting that authentication is present but poorly placed. This flaw lets unauthenticated attackers run arbitrary code on exposed servers by cleverly manipulating API endpoints.