Neural Network Testing, Verification & Repair: Home

Neural networks can be (arguably) viewed a different paradigm of programming, where logical reasoning is replaced with big data and optimization. Unlike traditional programs, however, neural networks are subject to bugs, e.g., adversarial samples and discriminatory instances. In this line of work, we aim to develop systematic theories, methods and tools to improve the quality of AI-systems.

SOCRATES is a unified platform for neural network analysis developed by Sun Jun's team at SMU. Unlike most existing neural network analysis approaches which are scattered (i.e., each approach tackles some restricted classes of neural networks against certain particular properties), incomparable (i.e., each approach has its own assumptions and input format) and thus hard to apply, reuse or extend, SOCRATES aims at providing a unified platform for neural network testing, verification and repair. Specifically, it supports a standardized format for a variety of neural network models, an asseration language for property specification as well as many engines for testing, verifying, and repairing neural network models. SOCRATES is still in active development. Any suggestions and collaborations are welcomed.

News

People

Faculty

SUN Jun

Research Fellows

PHAM Hong Long

ZHANG Peixin

PhD Students

SUN Bing

ZHANG Mengdi

ZHANG Ruihan

ZHAO Wei

WU Yufei

Alumni