Work

Revisiting Neural Program Smoothing for Fuzzing

Year: 2023

Type: conference-paper

Abstract: Testing with randomly generated inputs (fuzzing) has gained significant traction due to its capacity to expose program vulnerabilities automatically. Fuzz testing campaigns generate large amounts of data, making them ideal for the application of machine learning (ML). Neural program smoothing, a specific family of ML-guided fuzzers, aims to use a neural network as a smooth approximation of the program target for new test case generation.

Source: ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)

DOI: 10.1145/3611643.3616308

Authors: Maria-Irina Nicolae, Max Eisele, Andreas Zeller

Institutions: Robert Bosch (Germany), Saarland University, Helmholtz Center for Information Security

Language: English

Topic: Software Testing and Debugging Techniques

Subfield: Software

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Bundesministerium für Bildung und Forschung

Awards: Verbundprojekt: Effektives Testen von Cyber-physikalischen Systemen - CPSec -, Teilvorhaben: Effektives Testen von IoT Systemen, Verbundprojekt: Effektives Testen von Cyber-physikalischen Systemen - CPSec -, Teilvorhaben: Skalierbares und effizientes Fuzzing von zustandsbehafteter Software für eingebettete Systeme