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

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.

artificial intelligence attacks bad bots bard chatbots chatgpt cyberattacks and hacks data easy fix flaw generative generative ai google injection injection attacks open ai privacy prompt injection prompt injection attacks researchers security security flaw security researchers sort vulnerabilities vulnerable