Tool

CryptoKnight

CryptoKnight classifies compiled cryptographic primitives. It uses Intel Pin for dynamic instrumentation and PyTorch for the model. The README points to the 2018 paper in Information, DOI 10.3390/info9090231.

Targets: Binary
Category: Debugging and dynamic analysis
Relationship: Foundation tool
Sources reviewed: 2026-11-07

Stars: 40
Last commit: 2020-04-08
Language: Python
License (GitHub): Apache-2.0

GitHub data as of 2026-11-09

Copy as Markdown View JSON Cite

Requirements & limits

Install Python requirements, then run python knight.py --setup. Predicting a binary is python knight.py --predict. OpenSSL headers are needed to compile the sample binaries.
The README names no license.

Cite

BibTeX

@misc{cryptoknight,
  title = {{CryptoKnight}},
  howpublished = {\url{https://github.com/AbertayMachineLearningGroup/CryptoKnight}},
  url = {https://github.com/AbertayMachineLearningGroup/CryptoKnight},
  urldate = {2026-11-07},
  note = {Awesome REA entry: \url{https://awesomerea.org/resources/cryptoknight/}}
}

Plain text

CryptoKnight. https://github.com/AbertayMachineLearningGroup/CryptoKnight (accessed 2026-11-07). Awesome REA entry: https://awesomerea.org/resources/cryptoknight/

Useful? Star Awesome REA on GitHub2.4k

About this entry

The description was reviewed against primary sources.

Report an outdated entry Suggest a translation fix

Primary sources

README.md GitHub · AbertayMachineLearningGroup/CryptoKnight · Revision bdcd108