LLMs Demonstrate Significant Automated Cryptanalysis Capabilities in New Benchmark
A new preprint introduces CryptanalysisBench, a benchmark comprising 191 cryptanalysis tasks across six families of cryptographic primitives. Testing five frontier large language models, the study finds that these models can break 65-86% of Tier 1 (known-break) schemes and also produce novel attacks, including a key-recovery attack on SpoC AEAD and the identification of an error in KINDI's security proof. The benchmark is released to track AI progress in cryptanalysis and to stress-test cryptographic schemes.
Why it matters: This work highlights the rapidly advancing capability of LLMs to perform automated cryptanalysis, raising both opportunities and concerns for digital security.
Full story at: arXiv Cryptography and Security ↗