Chatbots like Open AI’s ChatGPT and Google’s Bard are vulnerable to indirect prompt injection attacks. Security researchers say the holes can be plugged—sort of.
Source: Wired – Threat Level
Generative AI’s Biggest Security Flaw Is Not Easy to Fix
- Smashing Security podcast #370: The closed loop conundrum, default passwords, and Baby Reindeer
- Cyberattack against United Russia claimed by Ukraine
- US jails former NSA employee for attempting secret sale to Russia
- Better identity threat detection sought by new Semperis ML-based tool
- Oasis Security reels in $35M more to secure nonhuman identities