.png){kind=icon}
返回
DeepMC: DNN test sample optimization method jointly guided by misclassification and coverage
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-022-04323-4.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Large-scale and high-quality test samples are extremely scarce in deep neural networks(DNN) testing. Existing test sample optimization methods exhibit the problem of low efficiency and low neuron coverage of optimized test samples, which consistently fail to expose erroneous behaviors of DNNs with corner-case inputs. In this paper, we propose DeepMC, an image classification DNN test sample optimization method jointly guided by misclassification and coverage. Specifically, we select the seed sample from the original test samples according to the misclassification probability. To maximize the misclassification probability and neuron coverage, we construct the joint optimization problem for the seed samples and use the gradient ascent to solve the joint optimization problem. We evaluate this method on two well-known datasets and prevalent image classification DNN models. Compare with DeepXplore, a DL white-box testing framework, DeepMC does not require multiple DNN models with similar functions for cross-referencing, saves 90% time consumption on MNIST, averagely covers 1.87% more neurons, and optimized test samples with more than 69% attack success rate. In addition, the test sample optimized by DeepMC can also be applied to optimize the robustness of the corresponding DNN with an average 3% improvement of the model's accuracy.
Keyword:
Deep neural networks
Testing
Neuron coverage
Misclassification probability
Test sample optimization
Image classification
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
暂无机构信息
引用论文
分享收藏A Two-Stage Generative Adversarial Networks With Semantic Content Constraints for Adversarial Example Generation具有语义内容约束的两阶段生成对抗网络，用于对抗示例生成.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏分享收藏
查看更多内容