Practical Binary Code Similarity Detection with BERT-based Transferable Similarity Learning
Sunwoo Ahn, Seonggwan Ahn, Hyungjoon Koo, Yunheung Paek
Abstract
Binary code similarity detection (BCSD) serves as a basis for a wide spectrum of applications, including software plagiarism, malware classification, and known vulnerability discovery. However, the inference of contextual meanings of a binary is challenging due to the absence of semantic information available in source codes. Recent advances leverage the benefits of a deep learning architecture into a better understanding of underlying code semantics and the advantages of the Siamese architecture into better BCSD.
Topics & Concepts
Computer scienceLeverage (statistics)Artificial intelligenceInferenceMalwareSimilarity (geometry)Binary numberCode (set theory)Natural language processingMachine learningProgramming languageSet (abstract data type)ArithmeticImage (mathematics)Operating systemMathematicsAdvanced Malware Detection TechniquesSoftware Engineering ResearchWeb Application Security Vulnerabilities