[HN Gopher] Perfectly secure steganography using minimum entropy...
       ___________________________________________________________________
        
       Perfectly secure steganography using minimum entropy coupling
        
       Author : Topolomancer
       Score  : 45 points
       Date   : 2023-05-21 16:39 UTC (1 days ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | nullc wrote:
       | Can 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?
        
       | kurthr wrote:
       | I 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.
        
         | wanderingbit wrote:
         | 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?
        
           | belter wrote:
           | 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.
        
         | wrycoder wrote:
         | Yes, the references in the paper are pretty interesting.
        
         | ajb wrote:
         | 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.
        
         | rahmeero wrote:
         | 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.
        
           | sacnoradhq wrote:
           | 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:
           | 
           | https://www.provos.org/p/outguess/
           | 
           | https://www.provos.org/p/detection-with-stegdetect/
        
       ___________________________________________________________________
       (page generated 2023-05-22 23:01 UTC)