Perfectly secure steganography using minimum entropy coupling
1–10 of 22 posts
Re: Perfectly secure steganography using minimum entropy coupling
#2I think it's the LLM (GPT2) link that makes this interesting to most since it allows relatively high data rate hidden/deniable communication through text interfaces.
Re: Perfectly secure steganography using minimum entropy coupling
#3I think it's the LLM (GPT2) link that makes this interesting to most since it allows relatively high data rate hidden/deniable communication through text interfaces.
Is this using steganography to create un-tamperable watermarks (which would allow downstream users of possibly-AI-created material to prove that it is indeed created by an AI) or, is this for something different?
Re: Perfectly secure steganography using minimum entropy coupling
#4I think it's the LLM (GPT2) link that makes this interesting to most since it allows relatively high data rate hidden/deniable communication through text interfaces.
Yes, the references in the paper are pretty interesting.
Re: Perfectly secure steganography using minimum entropy coupling
#5I think it's the LLM (GPT2) link that makes this interesting to most since it allows relatively high data rate hidden/deniable communication through text interfaces.
I can see how steganography applied to images can result in hard-to-detect watermarks or provenance identifiers.
But I don't see how these can be effectively used in text content. Yes, an AI program can encode provenance identifiers by length of words, starting letters of sentences, use of specific suffixes, and other linguistic constructs.
However, say that I am a student with an AI-generated essay and want to make sure my essay passes the professor's plagiarism checker. Isn't it pretty easy to re-order clauses, substitute synonyms, and add new content? In fact, I think there is even a Chrome extension that does something like that.
Or maybe that is too much work for the lazy student who wants to completely rely on ChatGTP or doesn't know any better.
Re: Perfectly secure steganography using minimum entropy coupling
#6I think it's the LLM (GPT2) link that makes this interesting to most since it allows relatively high data rate hidden/deniable communication through text interfaces.
It's been known for a long time that the bandwidth steganography is limited to the amount of randomness in the open data, eg Anderson and Peticolas "On the limits of steganography", '98 (I hope that's the right one anyway - a while since I read it). Which implies that if someone came up with a good reason to publish a bunch of high entropy randomness, the world would have much greater bandwidth of potential steganographic channels.
Now AI has done this for us. I suppose that under authoritarian regimes you will soon have to cryptographically prove that you generated your random bits deterministically from specific keys.
Re: Perfectly secure steganography using minimum entropy coupling
#7I think it's the LLM (GPT2) link that makes this interesting to most since it allows relatively high data rate hidden/deniable communication through text interfaces.
Is this using steganography to create un-tamperable watermarks (which would allow downstream users of possibly-AI-created material to prove that it is indeed created by an AI) or, is this for something different?
This is to transmit confidential information without using encryption. Something I predict will be more and more needed, as democratic governments succumb into their autocratic temptations and attempt to ban encryption.
Re: Perfectly secure steganography using minimum entropy coupling
#8Can someone who understands this work explain why using a range (de)coder to uncompress your ciphertext into the GPT2 generated distribution (in other words the most obvious construction for the case when the sender and receiver have the model) is insufficient to achieve perfect security by their definition?
Re: Perfectly secure steganography using minimum entropy coupling
#9I think it's the LLM (GPT2) link that makes this interesting to most since it allows relatively high data rate hidden/deniable communication through text interfaces.
I can see how steganography applied to images can result in hard-to-detect watermarks or provenance identifiers. But I don't see how these can be effectively used in text content. Yes, an AI program can encode provenance identifiers by length of words, starting letters of sentences, use of specific suffixes, and other linguistic constructs. However, say that I am a student with an AI-generated essay and want to make…
A higher level of abstraction generative AI will soon be able to apply is in the design of algorithms that humans cannot possibly comprehend that go well beyond rudimentary newspaper want ad spycraft.
Also, image based steg:
Re: Perfectly secure steganography using minimum entropy coupling
#10I think it's the LLM (GPT2) link that makes this interesting to most since it allows relatively high data rate hidden/deniable communication through text interfaces.
I can see how steganography applied to images can result in hard-to-detect watermarks or provenance identifiers. But I don't see how these can be effectively used in text content. Yes, an AI program can encode provenance identifiers by length of words, starting letters of sentences, use of specific suffixes, and other linguistic constructs. However, say that I am a student with an AI-generated essay and want to make…
The point of steganography (as discussed in the paper) is not unerasable watermarks but undetectable (to the adversary) messages in innocent-looking communication.
I'm confused why you focus on plagiarism detection. That being said, your scenario is very briefly mentioned in the conclusion and requires augmenting the approach (entropy coding) with error correction.
The result would be that as long as your modifications (reordering clauses, etc.) reasonably closely follow a known distribution with limited entropy (which I think it clearly does, although specifying this distribution and dealing with the induced noisy channel might be very hard), there will be a way to do covert communication despite it, though probably only a very small amount of information can be transmitted reliably. For plagiarism detection, you only need a number of bits that scales like -log[your desired false positive rate] so it would seem theoretically possible. Theoretically it also doesn't matter if you use text or images, though in practice increasing the amount of transmitted data should make the task a lot easier. However, I'm not sure if something like this can be practically implemented using existing methods.