Learning to Protect Communications with Adversarial Neural Cryptography · HackerPapers discussions

Learning to Protect Communications with Adversarial Neural Cryptography — mentioned by lkowalcz

Mon, 07 Aug 2017 18:35:20 GMT

I've never heard of neural encryption before, do you have a good source for me? From the Wikipedia page for "Neural cryptography", it seems like there's some success in using NN's for cryptanalysis, but not for constructions... Edit: Do you mean the Google GAN experiment? (https://arxiv.org/pdf/1610.06918v1.pdf) Ahh ok, well at least for this there looks like an attempt at defining a security model (security against some other NN). I don't really believe the security model is realistic (how do we know NN's are really that effective as adversaries?), but at least there is a model, so calling…

Paper and discussion history. A mention is not an endorsement.

Learning to Protect Communications with Adversarial Neural Cryptography — mentioned by proofofstake

Mon, 07 Aug 2017 18:27:37 GMT

Do you think neural encryption is closer to encryption? GAN-style: One network encrypts while preserving structure, another network tries to reverse engineer to the original features. Edit: No specific sources for what Numerai is using, but in general: https://arxiv.org/abs/1610.06918 "Learning to Protect Communications with Adversarial Neural Cryptography". Edit2: Yes, in general. I would say "yes, this is a valid form of encryption". But I do agree that their marketing was perhaps a bit too optimistic. I have no problem calling it "obfuscation" either (I just think their method of…

Paper and discussion history. A mention is not an endorsement.

Learning to Protect Communications with Adversarial Neural Cryptography — HN submission

Sun, 13 Nov 2016 21:18:19 GMT

Learning to Protect Communications with Adversarial Neural Cryptography

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Learning to Protect Communications with Adversarial Neural Cryptography — HN submission

Tue, 08 Nov 2016 07:44:04 GMT

Learning to Protect Communications with Adversarial Neural Cryptography

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Learning to Protect Communications with Adversarial Neural Cryptography — mentioned by ecesena

Fri, 28 Oct 2016 16:47:05 GMT

The paper [1] is by Abadi [2], which is a pretty big name in crypto. So I can assume it's something with value, wether the press can or can't convey that is another story. [1] https://arxiv.org/pdf/1610.06918v1.pdf [2] https://en.wikipedia.org/wiki/Mart%C3%ADn_Abadi

Paper and discussion history. A mention is not an endorsement.

Learning to Protect Communications with Adversarial Neural Cryptography — HN submission

Fri, 28 Oct 2016 14:30:02 GMT

Google Brain creates its own encryption methodology [paper]

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Learning to Protect Communications with Adversarial Neural Cryptography — mentioned by gcr

Fri, 28 Oct 2016 14:16:22 GMT

Please don't editorialize. Finding the best parameters that optimize an objective function can hardly be called "re-writing its own code." Granted, the article is just as guilty. (Edit: The article also doesn't mention self-modifying code so I'm not sure where you're getting that idea from.) For the curious, here is the preprint: https://arxiv.org/pdf/1610.06918v1.pdf The technique is an off-the-shelf GAN that attempts to learn a transformation (not arbitrary code!) from input to encrypted output. The learned model is not Turing complete, and most importantly, is _not_ self-modifying. The…

Paper and discussion history. A mention is not an endorsement.

Learning to Protect Communications with Adversarial Neural Cryptography — mentioned by trungaczne

Fri, 28 Oct 2016 13:21:32 GMT

This is the link to the research paper ("Learning to protect communications with adversarial neural cryptography"): https://arxiv.org/abs/1610.06918

Paper and discussion history. A mention is not an endorsement.

Learning to Protect Communications with Adversarial Neural Cryptography — HN submission

Thu, 27 Oct 2016 13:05:04 GMT

Google's Neural Network Invents Its Own Encryption

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Learning to Protect Communications with Adversarial Neural Cryptography — HN submission

Thu, 27 Oct 2016 00:05:13 GMT

Learning to Protect Communications with Adversarial Neural Cryptography

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.