pull down to refresh
33 sats \ 2 replies \ @optimism 10 Nov \ on: Whisper Leak: A novel side-channel attack on remote language models AI
There's this obfuscation extension built into mullvad called DAITA - I'm not sure how well it works though, as with the background noise it's only protecting the tunnel, not the tls going through the endpoint.
At least they built a nonce into these APIs now, that's good for an outside observer. But many of these chatbot sites require you to log in for more than trivial usage, so they will still correlate all your traffic to your chats anyway. I wouldn't take a bet against these guys selling that data either.
Thus, localhost LLM > intranet LLM > extranet LLM > internet LLM > LLM service.
Better to have some defense than none. It’s the usual cat-and-mouse game, sadly, the bad guys are pretty much always a step ahead.