New Anthropic research: Discovering cryptographic weaknesses with Claude.
Claude Mythos Preview has helped our researchers find weaknesses in cryptographic algorithms—the mathematical methods that are used to keep data private.
Read more: anthropic.com/research/disco…
Claude Mythos Preview has helped our researchers find weaknesses in cryptographic algorithms—the mathematical methods that are used to keep data private.
Read more: anthropic.com/research/disco…
Claude discovered weaknesses in a highly-secure digital signature scheme (used to verify identity digitally) and a well-known symmetric cipher (used to encrypt data).
The digital signature scheme is HAWK, which is designed to be robust even against hypothetical quantum computers.
HAWK has survived two years of expert review, but in 60 hours Mythos Preview found a previously-unknown attack that reduced the scheme’s key strength by half.
HAWK has survived two years of expert review, but in 60 hours Mythos Preview found a previously-unknown attack that reduced the scheme’s key strength by half.
The symmetric cipher is a reduced version of the Advanced Encryption Standard (AES)—which has received decades of scrutiny (more than almost any other encryption algorithm).
In a week, Mythos Preview found a way to speed up an attack on this version of AES by 200-800×.
In a week, Mythos Preview found a way to speed up an attack on this version of AES by 200-800×.
Mythos Preview did most of this work autonomously, with occasional human guidance. Each of the two results cost roughly $100,000 in API usage.
We disclosed the findings in advance to the algorithms’ authors, as well as to US government and industry partners.
We disclosed the findings in advance to the algorithms’ authors, as well as to US government and industry partners.
These are substantial research advances, but they don’t have a practical impact on today’s systems. HAWK is a proposed scheme that hasn’t been deployed anywhere, and the AES attack we discovered was on a weaker version and does not break the full cipher.
Still, both results show that frontier AI models are capable of doing expert-level cryptography research. This has important defensive applications—testing the algorithms that keep our online activity secure, and ultimately helping to make digital systems safer.
Full technical details of both attacks are provided in our new papers:
On HAWK: anthropic.com/document/hawk_…
On AES: anthropic.com/document/aes_m…
And the associated model chain-of-thought for AES: anthropic.com/document/aes_m…
On HAWK: anthropic.com/document/hawk_…
On AES: anthropic.com/document/aes_m…
And the associated model chain-of-thought for AES: anthropic.com/document/aes_m…
We also worked with academics at ETH Zurich, Tel Aviv University, and the University of Haifa to build CryptanalysisBench, a benchmark for studying LLMs’ cryptanalysis abilities.
arxiv.org/abs/2607.18538
arxiv.org/abs/2607.18538
• • •
Missing some Tweet in this thread? You can try to
force a refresh
