H@ckers can read encrypted AI chats

Topic

New Reply

Interesting article dated 14th March 2024 by Dan Goodin

Ref: arstechnica

All non-Google chat GPTs affected by side channel that leaks responses sent to users…

Yup, that includes Copilot, which is demonstrated within the above article.

Token Privacy

“Currently, anybody can read private chats sent from ChatGPT and other services,” Yisroel Mirsky, head of the Offensive AI Research Lab at Ben-Gurion University in Israel, wrote in an email. “This includes malicious actors on the same Wi-Fi or LAN as a client (e.g., same coffee shop), or even a malicious actor on the Internet—anyone who can observe the traffic…”

If debian is good enough for NASA...

3 users thanked author for this post.

windbg, Alex5723, NaNoNyMouse

Reply | Quote

Replies

Response (not input) guessed with 29% accuracy if network breached:

An additional challenge is establishing the means to observe packets the chatbot sends to an end user. This capability is relatively straightforward when both the target and adversary are on the same network but is much harder when they’re not, unless the attacker is a nation state or has fine-grained access inside an ISP.

Reply | Quote