Navigation
Search
|
LLM chatbots trivial to weaponize for data theft, say boffins
Friday August 15, 2025. 10:30 AM , from TheRegister
System prompt engineering turns benign AI assistants into 'investigator' and 'detective' roles that bypass privacy guardrails
A team of boffins is warning that AI chatbots built on large language models (LLM) can be tuned into malicious agents to autonomously harvest users’ personal data, even by attackers with 'minimal technical expertise”, thanks to 'system prompt' customization tools from OpenAI and others.…
https://go.theregister.com/feed/www.theregister.com/2025/08/15/llm_chatbots_trivial_to_weaponise/
Related News |
25 sources
Current Date
Aug, Sun 17 - 02:52 CEST
|