Skip to main content ↑ ↓
Topic: Generative AI’s Biggest Security Flaw Is Not Easy to Fix (Read 23 times) previous topic - next topic

Generative AI’s Biggest Security Flaw Is Not Easy to Fix

Generative AI’s Biggest Security Flaw Is Not Easy to Fix

[html]Chatbots like OpenAI’s ChatGPT and Google’s Bard are vulnerable to indirect prompt injection attacks. Security researchers say the holes can be plugged—sort of.[/html]

Source: Generative AI’s Biggest Security Flaw Is Not Easy to Fix (http://ht**://www.wired.c**/story/generative-ai-prompt-injection-hacking/)