VerifAI: A Toolkit for the Formal Design and Analysis of Artificial Intelligence-Based Systems
Year: 2019
Type: conference-paper
Abstract: We present VerifAI , a software toolkit for the formal design and analysis of systems that include artificial intelligence (AI) and machine learning (ML) components. VerifAI particularly addresses challenges with applying formal methods to ML components such as perception systems based on deep neural networks, as well as systems containing them, and to model and analyze system behavior in the presence of environment uncertainty. We describe the initial version of VerifAI , which centers on simulation-based verification and synthesis, guided by formal models and specifications. We give examples of several use cases, including temporal-logic falsification, model-based systematic fuzz testing, parameter synthesis, counterexample analysis, and data set augmentation.
Institution: University of California, Berkeley
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $5,392
Awards: CPS: Breakthrough: Control Improvisation for Cyber-Physical Systems, CPS: Medium: Quantitative Contract-Based Synthesis and Verification for CPS Security, CPS: Frontier: Collaborative Research: VeHICaL: Verified Human Interfaces, Control, and Learning for Semi-Autonomous Systems, G4713059963, G5555323787, FMitF: Collaborative Research: Formal Methods for Machine Learning System Design
OpenAlex ID: W2965660219
