You see what I want you to see: poisoning vulnerabilities in neural code search
Yao Wan, Shijie Zhang, Hongyu Zhang, Yulei Sui, Guandong Xu, Dezhong Yao, Hai Jin, Lichao Sun
2022Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering53 citationsDOI
Abstract
Searching and reusing code snippets from open-source software repositories based on natural-language queries can greatly improve programming productivity.Recently, deep-learning-based approaches have become increasingly popular for code search. Despite substantial progress in training accurate models of code search, the robustness of these models has received little attention so far.
Topics & Concepts
Computer scienceRobustness (evolution)Code reuseReuseCode (set theory)Search-based software engineeringSource codeCode reviewArtificial intelligenceMachine learningSoftwareProgramming languageWorld Wide WebComputer securitySoftware qualitySoftware developmentSoftware constructionEngineeringGeneWaste managementSet (abstract data type)ChemistryBiochemistryAdversarial Robustness in Machine LearningSoftware Engineering ResearchAdvanced Malware Detection Techniques