Seven LLMs succeed only on ciphers common in pretraining data, and few-shot examples help mostly for easy ciphers, in a new 4,509-sample cryptanalysis benchmark.
InFindings of the Association for Computational Linguistics: EMNLP 2024, pages 5094–5109, Miami, Florida, USA
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities
Seven LLMs succeed only on ciphers common in pretraining data, and few-shot examples help mostly for easy ciphers, in a new 4,509-sample cryptanalysis benchmark.