A Smart Contract Vulnerability Detection Model Based on Syntactic and Semantic Fusion Learning

Table 4

Comparison of experimental results of each module.

		Accuracy	Precision	Recall	F1
ImplicitVisibility	CFG	86.08	85.96	87.74	86.84
	AST	88.00	92.76	83.60	87.94
	AST + CFG	89.00	87.58	92.04	89.75
IntegerOverflow	CFG	92.92	91.03	96.06	93.48
	AST	94.08	93.37	95.58	94.47
	AST + CFG	95.58	94.08	97.79	95.90
IntegerUnderflow	CFG	95.25	91.59	83.40	87.31
	AST	94.66	90.91	80.85	85.59
	AST + CFG	96.42	92.86	88.51	90.63
TimeDependency	CFG	95.42	89.33	86.64	87.96
	AST	98.25	96.48	92.24	95.42
	AST + CFG	98.25	97.52	94.85	94.81
Reentrancy	CFG	97.33	58.06	48.65	52.94
	AST	98.58	76.32	73.68	77.33
	AST + CFG	98.64	90.91	78.38	75.36