FuSeBMC AI: Acceleration of Hybrid Approach through Machine Learning

Kaled M. Alshmrany; Mohannad Aldughaim; Chenfeng Wei; Tom Sweet; Richard Allmendinger; Lucas C. Cordeiro

FuSeBMC AI: Acceleration of Hybrid Approach through Machine Learning

Kaled M. Alshmrany, Mohannad Aldughaim, Chenfeng Wei, Tom Sweet, Richard Allmendinger, Lucas C. Cordeiro

Research output: Preprint/Working paper › Preprint

39 Downloads (Pure)

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.

Original language	Undefined
Publication status	Published - 9 Apr 2024

Keywords

cs.CR

Access to Document

2404.06031v1

VeriBee: Source Code Security
Cordeiro, L. (Participant), Allmendinger, R. (Participant) & Alshmrany, K. (Participant)
Impact: Economic, Technological

Cite this

@techreport{1d98379ca39b4f66905465fd837afd81,

title = "FuSeBMC AI: Acceleration of Hybrid Approach through Machine Learning",

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.",

keywords = "cs.CR",

author = "Alshmrany, {Kaled M.} and Mohannad Aldughaim and Chenfeng Wei and Tom Sweet and Richard Allmendinger and Cordeiro, {Lucas C.}",

year = "2024",

month = apr,

day = "9",

language = "Undefined",

type = "WorkingPaper",

}

TY - UNPB

T1 - FuSeBMC AI

T2 - Acceleration of Hybrid Approach through Machine Learning

AU - Alshmrany, Kaled M.

AU - Aldughaim, Mohannad

AU - Wei, Chenfeng

AU - Sweet, Tom

AU - Allmendinger, Richard

AU - Cordeiro, Lucas C.

PY - 2024/4/9

Y1 - 2024/4/9

N2 - 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.

AB - 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.

KW - cs.CR

M3 - Preprint

BT - FuSeBMC AI

ER -

FuSeBMC AI: Acceleration of Hybrid Approach through Machine Learning

Abstract

Keywords

Access to Document

Impacts

VeriBee: Source Code Security

Cite this