Causality-based Neural Network Repair

by   Bing Sun, et al.

Neural networks have had discernible achievements in a wide range of applications. The wide-spread adoption also raises the concern of their dependability and reliability. Similar to traditional decision-making programs, neural networks can have defects that need to be repaired. The defects may cause unsafe behaviors, raise security concerns or unjust societal impacts. In this work, we address the problem of repairing a neural network for desirable properties such as fairness and the absence of backdoor. The goal is to construct a neural network that satisfies the property by (minimally) adjusting the given neural network's parameters (i.e., weights). Specifically, we propose CARE (CAusality-based REpair), a causality-based neural network repair technique that 1) performs causality-based fault localization to identify the `guilty' neurons and 2) optimizes the parameters of the identified neurons to reduce the misbehavior. We have empirically evaluated CARE on various tasks such as backdoor removal, neural network repair for fairness and safety properties. Our experiment results show that CARE is able to repair all neural networks efficiently and effectively. For fairness repair tasks, CARE successfully improves fairness by 61.91% on average. For backdoor removal tasks, CARE reduces the attack success rate from over 98% to less than 1%. For safety property repair tasks, CARE reduces the property violation rate to less than 1%. Results also show that thanks to the causality-based fault localization, CARE's repair focuses on the misbehavior and preserves the accuracy of the neural networks.


page 1

page 2

page 3

page 4


QNNRepair: Quantized Neural Network Repair

We present QNNRepair, the first method in the literature for repairing q...

Semantic-Based Neural Network Repair

Recently, neural networks have spread into numerous fields including man...

NNrepair: Constraint-based Repair of Neural Network Classifiers

We present NNrepair, a constraint-based technique for repairing neural n...

Adaptive Fairness Improvement Based on Causality Analysis

Given a discriminating neural network, the problem of fairness improveme...

Causal Repair of Learning-enabled Cyber-physical Systems

Models of actual causality leverage domain knowledge to generate convinc...

A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks

Counterexample-guided repair aims at creating neural networks with mathe...

Self-Repairing Neural Networks: Provable Safety for Deep Networks via Dynamic Repair

Neural networks are increasingly being deployed in contexts where safety...

Please sign up or login with your details

Forgot password? Click here to reset