A Survey of Automatic Software Vulnerability Detection, Program Repair, and Defect Prediction Techniques

Table 3

Technical characteristics of grammar-based clone detection.

System/writer	Data preprocessing	Code representation	Network	Clone types	Classification object
CCLearner [3]	Use ANTLR and ASRParser to parse each method	Token AST	DNN	T1–T3	Method pairs
CLDH [4]	Parse each code fragment to AST	AST	LSTM	T1–T4	code fragments
White et al. [5]	Use ANTLR to tokenize code	AST FBT olive trees	RtvNN	T1–T4	Method/file level
Marastoni et al. [6]	Leverage tigress C to obfuscate dataset	Binary image	CNN	T4	Image level