Year: 2025
Type: conference-paper
Abstract: Deep Neural Networks (DNNs) are increasingly deployed in critical applications, where ensuring their safety and robustness is paramount. We present $$_\text {CAV25}$$ CAV 25 , a high-performance DNN verification tool that uses the DPLL(T) framework and supports a wide-range of network architectures and activation functions. Since its debut in VNN-COMP’23, in which it achieved the New Participant Award and ranked 4th overall, $$_\text {CAV25}$$ CAV 25 has advanced significantly, achieving second place in VNN-COMP’24. This paper presents and evaluates the latest development of $$_\text {CAV25}$$ CAV 25 , focusing on the versatility, ease of use, and competitive performance of the tool. $$_\text {CAV25}$$ CAV 25 is available at: https://github.com/dynaroars/neuralsat .
Authors: Hai Duong, ThanhVu Nguyen, Matthew B. Dwyer
Institutions: George Mason University, University of Virginia
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $5,392
Funder: National Science Foundation
Awards: Collaborative Research: FMitF: Track II: From Theory to Practice: Making Complex Invariants Accessible with DIG, SHF: Small: Distribution-aware Testing for Neural Networks, Collaborative Research: SHF: Medium: Ensuring Safety and Liveness of Modern Systems through Dynamic Temporal Analysis, CAREER: NeuralSAT: A Constraint-Solving Framework for Verifying Deep Neural Networks, FMitF: Track II: Cybolic: a symbolic execution technique and tool for analyzing CMake build scripts, Collaborative Research: PPoSS: LARGE: Co-designing Hardware, Software, and Algorithms to Enable Extreme-Scale Machine Learning Systems, FMitF: Track I: Focusing Incremental Abstraction-based Verification on Neural Networks Input Distributions
OpenAlex ID: W4412514774