Recognizing Functions in Binaries with Neural Networks

@inproceedings{Shin2015RecognizingFI,
  title={Recognizing Functions in Binaries with Neural Networks},
  author={Eui Chul Richard Shin and Dawn Xiaodong Song and Reza Moazzezi},
  booktitle={USENIX Security Symposium},
  year={2015}
}
Binary analysis facilitates many important applications like malware detection and automatically fixing vulnerable software. In this paper, we propose to apply artificial neural networks to solve important yet difficult problems in binary analysis. Specifically, we tackle the problem of function identification, a crucial first step in many binary analysis techniques. Although neural networks have undergone a renaissance in the past few years, achieving breakthrough results in multiple… CONTINUE READING
Highly Cited
This paper has 65 citations. REVIEW CITATIONS

12 Figures & Tables

Extracted Numerical Results

  • For the function start identification problem, our methods consistently obtain F1 scores in the range of 98-99%.
  • Except on the ELF x86-64 dataset, this allows us to obtain 97-98% in F1 score.

Topics

Statistics

020402015201620172018
Citations per Year

65 Citations

Semantic Scholar estimates that this publication has 65 citations based on the available data.

See our FAQ for additional information.