Neural Nets Can Learn Function Type Signatures From Binaries

@inproceedings{Chua2017NeuralNC,
  title={Neural Nets Can Learn Function Type Signatures From Binaries},
  author={Zheng Leong Chua and Shiqi Shen and Prateek Saxena and Zhenkai Liang},
  booktitle={USENIX Security Symposium},
  year={2017}
}
Function type signatures are important for binary analysis, but they are not available in COTS binaries. In this paper, we present a new system called EKLAVYA which trains a recurrent neural network to recover function type signatures from disassembled binary code. EKLAVYA assumes no knowledge of the target instruction set semantics to make such inference. More importantly, EKLAVYA results are “explicable”: we find by analyzing its model that it auto-learns relationships between instructions… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 12 extracted citations

Debin: Predicting Debug Information in Stripped Binaries

ACM Conference on Computer and Communications Security • 2018
View 4 Excerpts
Highly Influenced

LEMNA: Explaining Deep Learning based Security Applications

ACM Conference on Computer and Communications Security • 2018
View 6 Excerpts
Highly Influenced

PANDORA: A Scalable and Efficient Scheme to Extract Version of Binaries in IoT Firmwares

2018 IEEE International Conference on Communications (ICC) • 2018
View 1 Excerpt

Tiresias: Predicting Security Events Through Deep Learning

ACM Conference on Computer and Communications Security • 2018
View 2 Excerpts

References

Publications referenced by this paper.
Showing 1-10 of 53 references

A Tough Call: Mitigating Advanced Code-Reuse Attacks at the Binary Level

2016 IEEE Symposium on Security and Privacy (SP) • 2016
View 4 Excerpts
Highly Influenced

Automatically Repairing Stripped Executables with CFG Microsurgery

2015 IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops • 2015
View 1 Excerpt

Software available from tensorflow.org

M. ABADI, A. AGARWAL, +36 authors YU Y.
2015
View 2 Excerpts

Strict protection for virtual function calls in cots c + + binaries

T. H OLZ, C. W ILLEMS, P. D ÜSSEL, P. L ASKOV
In NDSS • 2015

Similar Papers

Loading similar papers…