A stratified approach to function fingerprinting in program binaries using diverse features

作者：

Highlights：

• A key observation is that traditional features such as N-grams may not be reliable.

• Leverage a diverse set of static and dynamic features to form a robust fingerprint.

• Verifying the correctness of function fingerprinting findings.

摘要

•A key observation is that traditional features such as N-grams may not be reliable.•Leverage a diverse set of static and dynamic features to form a robust fingerprint.•Verifying the correctness of function fingerprinting findings.

论文关键词：Binary code,Machine learning,Reverse engineering

论文评审过程：Received 15 April 2021, Revised 23 October 2021, Accepted 6 December 2021, Available online 1 January 2022, Version of Record 5 January 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116384