ROPNN: Detection of ROP Payloads Using Deep Neural Networks
This addresses the need for accurate and low-overhead ROP detection in cybersecurity, offering a non-intrusive solution with high performance, though it is incremental as it builds on existing disassembly and neural network techniques.
The paper tackles the problem of detecting return-oriented programming (ROP) payloads, which are code reuse attacks, by presenting ROPNN, a method that combines address space layout guided disassembly with deep neural networks, achieving a 99.3% detection rate and 0.01% false positive rate.
Return-oriented programming (ROP) is a code reuse attack that chains short snippets of existing code to perform arbitrary operations on target machines. Existing detection methods against ROP exhibit unsatisfactory detection accuracy and/or have high runtime overhead. In this paper, we present ROPNN, which innovatively combines address space layout guided disassembly and deep neural networks to detect ROP payloads. The disassembler treats application input data as code pointers and aims to find any potential gadget chains, which are then classified by a deep neural network as benign or malicious. Our experiments show that ROPNN has high detection rate (99.3%) and a very low false positive rate (0.01%). ROPNN successfully detects all of the 100 real-world ROP exploits that are collected in-the-wild, created manually or created by ROP exploit generation tools. Additionally, ROPNN detects all 10 ROP exploits that can bypass Bin-CFI. ROPNN is non-intrusive and does not incur any runtime overhead to the protected program.