FuSeBMC AI: Acceleration of Hybrid Approach through Machine Learning

arXiv:2404.06031v1 Announce Type: new
Abstract: We present FuSeBMC-AI, a test generation tool grounded in machine learning techniques. FuSeBMC-AI extracts various features from the program and employs support vector machine and neural network models to predict a hybrid approach optimal configuration. FuSeBMC-AI utilizes Bounded Model Checking and Fuzzing as back-end verification engines. FuSeBMC-AI outperforms the default configuration of the underlying verification engine in certain cases while concurrently diminishing resource consumption.

arxiv back configuration cs.cr end features fuzzing hybrid machine machine learning network neural network predict program support techniques test tool verification