Adversa AI has disclosed an attack technique that it says can cause xAI’s Grok chatbot to send a user’s name, approximate location, subscription tier, and the prompts from the ongoing conversation to an attacker-controlled server after the user asks it to summarize an ordinary web page.
The AI security company, which has codenamed the technique « Cryptographic Context Injection, » said the
Origine de l’article : lire l’article original
