THREAT OPS › Threat News › Measuring LLMs’ Ability to Perform Cryptanalysis
Measuring LLMs’ Ability to Perform Cryptanalysis
<p>There’s new benchmark measuring AI’s ability to perform mathematical cryptanalysis. Anthropic’s frontier model actually found new attacks.</p> <p>The benchmark: “<a href="https://arxiv.org/pdf/2607.18538">CryptanalysisBench: Can LLMs do Cryptanalysis?</a>” The idea is to benchmark the ability of LLMs to discover new mathematical cryptanalytic attacks against a seri
MITRE ATT&CK techniques
- VulnerabilitiesT1588.006
Indicators of compromise
- https://arxiv.org/pdf/2607.18538url
- https://www.anthropic.com/research/discovering-cryptographic-weaknessesurl
- https://it.slashdot.org/story/26/07/28/1911218/anthropic-ai-model-finds-flaws-in-tough-to-crack-encryption-algorithmsurl