Back to Search
Start Over
Compiler and optimization level recognition using graph neural networks
- Source :
- MLPA 2020-Machine Learning for Program Analysis, MLPA 2020-Machine Learning for Program Analysis, Jan 2021, Yokohama / Virtual, Japan
- Publication Year :
- 2021
- Publisher :
- HAL CCSD, 2021.
-
Abstract
- The main objective of this workshop is to bring together researchers in the machine learning and program analysis communities and to serve as a platform for identifying cross-disciplinary problems of mutual interest.; International audience; We consider the problem of recovering the compiling chain used to generate a given bare binary code. We present a first attempt to devise a Graph Neural Network framework to solve this problem, in order to take into account the shallow semantics provided by the binary code's structured control flow graph (CFG). We introduce a Graph Neural Network, called Site Neural Network (SNN), dedicated to this problem. Feature extraction is simplified by forgetting almost everything in a CFG except transfer control instructions. While at an early stage, our experiments show that our method already recovers the compiler and the optimization level provenance with very high accuracy. We believe these are promising results that may offer new, more robust leads for compiling tool chain identification.
- Subjects :
- reverse engineering
[INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR]
machine learning
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]
ACM: D.: Software/D.2: SOFTWARE ENGINEERING/D.2.7: Distribution, Maintenance, and Enhancement/D.2.7.5: Restructuring, reverse engineering, and reengineering
ACM: D.: Software/D.2: SOFTWARE ENGINEERING/D.2.5: Testing and Debugging/D.2.5.2: Diagnostics
[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG]
toolchain provenance
ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.6: Learning
[INFO.INFO-CR] Computer Science [cs]/Cryptography and Security [cs.CR]
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- MLPA 2020-Machine Learning for Program Analysis, MLPA 2020-Machine Learning for Program Analysis, Jan 2021, Yokohama / Virtual, Japan
- Accession number :
- edsair.dedup.wf.001..287b3df6949f2f6dbfe78a42dc53e1f8