CryptanalysisBench: Can LLMs Do Cryptanalysis?

A new benchmark, CryptanalysisBench, shows that five frontier large language models can break 65%-86% of Tier 1 cryptographic schemes and produce novel cryptanalysis, including a key-recovery attack on SpoC AEAD and an error in KINDI's CCA-security proof. The benchmark, introduced by researchers and comprising 191 tasks across six families of cryptographic primitives, evaluates models including Claude Opus 4.8, Sonnet 5, Mythos 5, GPT 5.5, and GLM 5.2, finding that AI cryptanalysis is approaching the published state of the art.

Computer Science Cryptography and Security Submitted on 20 Jul 2026 Title:CryptanalysisBench: Can LLMs do Cryptanalysis? View PDF /pdf/2607.18538 HTML experimental https://arxiv.org/html/2607.18538v1 Abstract:Cryptanalysis - the task of finding attacks against cryptographic schemes - sits at the intersection of mathematical reasoning and cybersecurity, two areas where LLMs have advanced fastest. Cryptanalysis represents both a clean testbed for frontier reasoning as practical attacks can be automatically verified and a domain with unusually high stakes, since the primitives under study underpin our digital security. In this paper we ask whether LLMs can do cryptanalysis, and find that the answer is increasingly yes. We introduce CryptanalysisBench, 191 tasks across six families of cryptographic primitives block ciphers, hash functions, etc. drawn primarily from four NIST standardization competitions. Our benchmark consists of three tiers: i primitives with known practical breaks; ii primitives with no known practical break, evaluated both at full strength and as scaled-down variants; and iii a challenge set of production primitives at the frontier of cryptanalysis. Five frontier models Claude Opus 4.8, Sonnet 5, Mythos 5, GPT 5.5, and the open-weights GLM 5.2 break 65%-86% of Tier 1 schemes, 6-12 Tier-2 schemes at full strength, and 24-61 across all scaled-down variants. Beyond deriving known results, models produce novel cryptanalysis, such as a key-recovery attack that exploits a design flaw in the SpoC AEAD and an error in KINDI's published CCA-security proof, both to the best of our knowledge not previously known. We release CryptanalysisBench as a tool to help track if or when AI cryptanalysis becomes a serious factor and as a scaffold for stress-testing candidate schemes before deployment. The attacks that the benchmark already surfaces are an early snapshot of a fast-moving frontier that may soon match, and in places exceed, the published state of the art. References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .