DeepSensor: Deep Learning Testing Framework Based on Neuron Sensitivity

by   Haibo Jin, et al.
HUAWEI Technologies Co., Ltd.
National University of Defense Technology
Zhejiang University of Technology

Despite impressive capabilities and outstanding performance, deep neural network(DNN) has captured increasing public concern for its security problem, due to frequent occurrence of erroneous behaviors. Therefore, it is necessary to conduct systematically testing before its deployment to real-world applications. Existing testing methods have provided fine-grained criteria based on neuron coverage and reached high exploratory degree of testing. But there is still a gap between the neuron coverage and model's robustness evaluation. To bridge the gap, we observed that neurons which change the activation value dramatically due to minor perturbation are prone to trigger incorrect corner cases. Motivated by it, we propose neuron sensitivity and develop a novel white-box testing framework for DNN, donated as DeepSensor. The number of sensitive neurons is maximized by particle swarm optimization, thus diverse corner cases could be triggered and neuron coverage be further improved when compared with baselines. Besides, considerable robustness enhancement can be reached when adopting testing examples based on neuron sensitivity for retraining. Extensive experiments implemented on scalable datasets and models can well demonstrate the testing effectiveness and robustness improvement of DeepSensor.


page 1

page 8

page 10


An Overview of Structural Coverage Metrics for Testing Neural Networks

Deep neural network (DNN) models, including those used in safety-critica...

CatchBackdoor: Backdoor Testing by Critical Trojan Neural Path Identification via Differential Fuzzing

The success of deep neural networks (DNNs) in real-world applications ha...

Interpreting and Improving Adversarial Robustness with Neuron Sensitivity

Deep neural networks (DNNs) are vulnerable to adversarial examples where...

Fostering the Robustness of White-Box Deep Neural Network Watermarks by Neuron Alignment

The wide application of deep learning techniques is boosting the regulat...

Is Neuron Coverage Needed to Make Person Detection More Robust?

The growing use of deep neural networks (DNNs) in safety- and security-c...

Revisiting Neuron Coverage Metrics and Quality of Deep Neural Networks

Deep neural networks (DNN) have been widely applied in modern life, incl...

White-box Testing of NLP models with Mask Neuron Coverage

Recent literature has seen growing interest in using black-box strategie...

Please sign up or login with your details

Forgot password? Click here to reset