CREBench benchmark finds frontier LLMs recover cryptographic flags in 59% of cases versus 92% for human experts.
Model Output
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering
CREBench benchmark finds frontier LLMs recover cryptographic flags in 59% of cases versus 92% for human experts.