Re:Perfectly Secure Steganography Using Minimum Entropy Coup...
by nullc on Monday May 22, 2023 @07:00PM
(#36037795)
This is fairly theoretical work. It assumes that the parties (and the adversary) know the distribution precisely.
Its direct practical may be potentially somewhat limited because people aren't going around communicating randomly selected LLM outputs... and if you use LLM output in a context where text would be expected it could be distinguished.
It's not useful for watermarking as the first change will destroy all the rest of the embedding.
I can make a contrived example where it's directly useful: Imagine you have agents in the field, you could send out LLM generated spam to communicate with them. Everyone expects the spam to be LLM generated, so it's not revealing that its detectable as such. This work discusses how you can make the spam carry secret messages to the agents in a way that is impossible to detect (without the key, of course) even by an attacker that has the exact spam LLM.
But really, even if the situation it solves is too contrived to be a gain over alternatives, the context provides an opportunity to explore the boundary of what is possible.
Its direct practical may be potentially somewhat limited because people aren't going around communicating randomly selected LLM outputs... and if you use LLM output in a context where text would be expected it could be distinguished.
It's not useful for watermarking as the first change will destroy all the rest of the embedding.
I can make a contrived example where it's directly useful: Imagine you have agents in the field, you could send out LLM generated spam to communicate with them. Everyone expects the spam to be LLM generated, so it's not revealing that its detectable as such. This work discusses how you can make the spam carry secret messages to the agents in a way that is impossible to detect (without the key, of course) even by an attacker that has the exact spam LLM.
But really, even if the situation it solves is too contrived to be a gain over alternatives, the context provides an opportunity to explore the boundary of what is possible.