LLMs won't break symmetric crypto • Hacker News Board

Re: LLMs won't break symmetric crypto

#41

Post by tptacek » Thu, Aug 06, 2026, 3:37 AM UTC

cyberax wrote: post #37

modeless wrote: post #7

I don't really find the "because it's difficult" arguments convincing at all. Especially the one claiming it's hard because it requires designing and running a large number of tests and reasoning about the results of each one. That kind of tedious grinding is exactly where LLMs should shine vs humans! The only convincing argument here is that these things are battle tested (literally in most cases I would guess), wit…

There are very few computer-era symmetric ciphers that were truly broken. RC4 is probably the worst example. There are no reasonable attacks even on the good old DES. And by "reasonable" I mean attacks that would bring down the complexity to a practical level if the DES key size were to be extended to something like 128 bits. We can brute-force DES keys trivially, but that's not a fault of the cipher per se.

RC4 is a good example of what Aumasson means when he jokes about weak symmetric cryptography being a quirk of history. It's genuinely weird that RC4 was as popular as it was! DES is broken because it's small, with tiny keys and an 8-byte block. But if it had 16-byte keys and blocks, and presumably a higher round count, the only dealbreaker with it might be that it'd be slow.

Re: LLMs won't break symmetric crypto

#42

Post by tptacek » Thu, Aug 06, 2026, 3:38 AM UTC

arberx wrote: post #13

LLMs will accelerate math research, increasing understanding in areas like quantum which will eventually lead to breakthroughs that will break most standard asymmetric encryption algorithms with the side effect of breaking crypto

Right, maybe, but Aumasson's whole point is that this prediction doesn't apply to AES, SHA2, BLAKE2, &c.

Re: LLMs won't break symmetric crypto

#43

Post by danielmarkbruce » Thu, Aug 06, 2026, 3:39 AM UTC

tptacek wrote: post #36

danielmarkbruce wrote: post #25

This is kind of a stupid argument. How about make a slightly stronger claim like "models won't break symmetric crypto" ? I mean, language models aren't even trained to break symmetric crypto. There is not good reason to think they will. It seems possible to train a large model to do it though.

To train a large model to do what? Break AES? How would that work?

Train on plaintext, ciphertext -> key.

Re: LLMs won't break symmetric crypto

#44

Post by tptacek » Thu, Aug 06, 2026, 3:40 AM UTC

whateveracct wrote: post #3

okay so silicon valley won't happen all the way

Silicon Valley does an elliptic curve attack; it doesn't break symmetric cryptography.

Re: LLMs won't break symmetric crypto

#45

Post by tptacek » Thu, Aug 06, 2026, 3:42 AM UTC

stingraycharles wrote: post #12

zkmon wrote: post #9

Cryptographic systems are based on 1) mathematical impossibility of reversing some integer/mod calculation, 2) time required for a brute force attack, 3) correctness of algorithms and code used in implementations. The last part (algorithms and code) is where LLMs have a chance. The first one is not similar to the mathematical breakthroughs LLMs are making recently. There is a loss of information in mods and integer c…

Yeah, I wouldn’t say with certainty that LLMs will never break any symmetrical crypto algorithm. It will certainly require a lot of effort, but so does solving some hard math challenges and it has been proven successful in that in the past. Most likely outcome will be that a security researcher is able to break one with assistance of / in collaboration with an LLM.

Symmetric cryptography isn't based on complicated math the way asymmetric cryptography it is. The right way to think about symmetric cryptography is that the core hard problem is simply making PLAINTEXT XOR KEY work, efficiently, with a key that repeats.

Re: LLMs won't break symmetric crypto

#46

Post by tptacek » Thu, Aug 06, 2026, 3:42 AM UTC

danielmarkbruce wrote: post #43

tptacek wrote: post #36

Earlier quoted context omitted.

To train a large model to do what? Break AES? How would that work?

Train on plaintext, ciphertext -> key.

LLMs aren't literally science fiction.

Re: LLMs won't break symmetric crypto

#47

Post by danielmarkbruce » Thu, Aug 06, 2026, 3:44 AM UTC

catlifeonmars wrote: post #27

danielmarkbruce wrote: post #25

This is kind of a stupid argument. How about make a slightly stronger claim like "models won't break symmetric crypto" ? I mean, language models aren't even trained to break symmetric crypto. There is not good reason to think they will. It seems possible to train a large model to do it though.

Agreed that many of the articles claims are a bit weak. One point is reasonably strong though: symmetric crypto may not be breakable (battle tested).

It probably isn't. But if you laid 20-1 I'd bet a large model will break an industry used standard within 10 years. That's a loose framing of a bet, but I think you get my point, even if you think my numbers suggest too much optimism.

Re: LLMs won't break symmetric crypto

#48

Post by danielmarkbruce » Thu, Aug 06, 2026, 3:45 AM UTC

tptacek wrote: post #46

danielmarkbruce wrote: post #43

Earlier quoted context omitted.

Train on plaintext, ciphertext -> key.

LLMs aren't literally science fiction.

Well, again, i'm not talking about a language model....

And, just because what I'm saying isn't especially likely to work, it's not obvious that it cannot. Very large models are doing all manner of things that very smart people thought were not possible just 6 or 7 years ago.

Re: LLMs won't break symmetric crypto

#49

Post by TheDong » Thu, Aug 06, 2026, 3:55 AM UTC

arberx wrote: post #13

LLMs will accelerate math research, increasing understanding in areas like quantum which will eventually lead to breakthroughs that will break most standard asymmetric encryption algorithms with the side effect of breaking crypto

What makes your prediction more likely than:

"LLMs will accelerate math research, allowing us to prove that meaningfully sized quantum computers are impossible and crypto is secure. Modern cryptographic algorithms remains unbroken until the last human is turned into a paperclip in the year 2430"

Re: LLMs won't break symmetric crypto

#50

Post by insanitybit » Thu, Aug 06, 2026, 3:58 AM UTC

danielmarkbruce wrote: post #48

tptacek wrote: post #46

Earlier quoted context omitted.

LLMs aren't literally science fiction.

Well, again, i'm not talking about a language model.... And, just because what I'm saying isn't especially likely to work, it's not obvious that it cannot. Very large models are doing all manner of things that very smart people thought were not possible just 6 or 7 years ago.

It's unclear what you are talking about then. Because the idea of training "ciphertext -> plaintext" for language models is absolutely bonkers, so what are you suggesting?