
Research Article
Neural Representation Learning Based Binary Code Authorship Attribution
4 downloads
@INPROCEEDINGS{10.1007/978-3-030-68734-2_15, author={Zhongmin Wang and Zhen Feng and Zhenzhou Tian}, title={Neural Representation Learning Based Binary Code Authorship Attribution}, proceedings={Digital Forensics and Cyber Crime. 11th EAI International Conference, ICDF2C 2020, Boston, MA, USA, October 15-16, 2020, Proceedings}, proceedings_a={ICDF2C}, year={2021}, month={2}, keywords={Authorship attribution Binary code Neural network Representation learning}, doi={10.1007/978-3-030-68734-2_15} }
- Zhongmin Wang
Zhen Feng
Zhenzhou Tian
Year: 2021
Neural Representation Learning Based Binary Code Authorship Attribution
ICDF2C
Springer
DOI: 10.1007/978-3-030-68734-2_15
Abstract
Authorship attribution on binary code is of great value in applications such as malware analysis, software forensics, and code theft detection. Inspired by the recent great successes of neural network and representation learning in various program analysis tasks, this study proposes NMPI to achieve fine-grained program authorship attribution by analyzing the binary codes of individual functions from the perspective of sequence and structural. To evaluate the NMPI, the study constructs a large dataset consisting of 268796 functions collected from Google CodeJam. The extensive experimental evaluation shows that NMPI can achieve 91% accuracy for the function-level binary code authorship attribution task.
Copyright © 2020–2025 ICST