Researchers at the University of Texas at Austin discovered a new attack method called ConfusedPilot. This method targets Retrieval Augmented Generation (RAG) based AI systems and allows the manipulation of AI systems.
Source: Security Magazine
Research uncovers new attack method, security leaders share insights
- Cybercriminals Exploiting Docker API Servers for SRBMiner Crypto Mining Attacks
- Cranium Detect AI accelerates AI governance
- Security Flaw in Styra’s OPA Exposes NTLM Hashes to Remote Attackers
- The AI Fix #21: Virtual Trump, barking mad AI, and a robot dog with a flamethrower
- SailPoint Machine Identity Security reduces the risk associated with unmanaged machine identities