AI chatbots can be tricked by hackers into helping them stealing your private data.
Read more in my article on the Bitdefender blog: https://www.bitdefender.com/en-us/blog/hotforsecurity/ai-chatbots-can-be-tricked-by-hackers-into-stealing-your-data/
#cybersecurity #ai #llm
@[email protected] @[email protected] have you seen the work on using non printing characters to poison llm prompts and exfiltrate data from victims? Unicode is dangerous 🤪
https://jeredsutton.com/post/llm-unicode-prompt-injection/