SOCRATES: Towards a Unified Platform for Neural Network Verification

by   Long H. Pham, et al.

Studies show that neural networks, not unlike traditional programs, are subject to bugs, e.g., adversarial samples that cause classification errors and discriminatory instances that demonstrate the lack of fairness. Given that neural networks are increasingly applied in critical applications (e.g., self-driving cars, face recognition systems and personal credit rating systems), it is desirable that systematic methods are developed to verify or falsify neural networks against desirable properties. Recently, a number of approaches have been developed to verify neural networks. These efforts are however 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. In this project, we aim to build a unified framework for developing verification techniques for neural networks. Towards this goal, we develop a platform called SOCRATES which supports a standardized format for a variety of neural network models, an assertion language for property specification as well as two novel algorithms for verifying or falsifying neural network models. SOCRATES is extensible and thus existing approaches can be easily integrated. Experiment results show that our platform offers better or comparable performance to state-of-the-art approaches. More importantly, it provides a platform for synergistic research on neural network verification.


page 1

page 3


Towards Repairing Neural Networks Correctly

Neural networks are increasingly applied to support decision making in s...

An Abstraction-Based Framework for Neural Network Verification

Deep neural networks are increasingly being used as controllers for safe...

Provable Fairness for Neural Network Models using Formal Verification

Machine learning models are increasingly deployed for critical decision-...

Probabilistic Verification of Neural Networks Against Group Fairness

Fairness is crucial for neural networks which are used in applications w...

Expediting Neural Network Verification via Network Reduction

A wide range of verification methods have been proposed to verify the sa...

Neural Network Verification through Replication

A system identification based approach to neural network model replicati...

Verifying Neural Networks Against Backdoor Attacks

Neural networks have achieved state-of-the-art performance in solving ma...

Please sign up or login with your details

Forgot password? Click here to reset