Weight-based Semantic Testing Approach for Deep Neural Networks
Weight-based Semantic Testing Approach for Deep Neural Networks
复制标题
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Amany Alshareef;Nicolas Berthier;Sven Schewe;Xiaowei Huang
中科院分区：
文献类型：
--
作者：
Amany Alshareef;Nicolas Berthier;Sven Schewe;Xiaowei Huang
虽然深度学习模型在各个领域都取得了最先进的性能，但它们对对抗性示例的敏感性引起了人们对其在安全关键领域的应用的严重担忧。现有的测试方法未能考虑神经元之间的相互作用以及通过训练过程在 DNN 中形成的语义表示。本文提出了一种基于权重的测试指标，该指标使用特征重要性权重来衡量测试集的覆盖范围，并有助于生成针对更高权重特征的附加测试用例。进行评估以将所提出的加权方法的初始和最终覆盖率与正常的基于 BN 的特征覆盖率进行比较。测试覆盖率实验表明，与原始特征指标相比，所提出的权重指标实现了更高的覆盖率，同时保持了在测试用例生成过程中寻找对抗性样本的有效性。
While deep learning models have achieved state-of-the-art performance in a variety of fields, their susceptibility to adversarial examples has raised serious concerns over their application in safety-critical domains. Existing testing methodologies fail to consider interactions between neurons and the semantic representation that formed in the DNN through the training process. This paper proposes a weight-based testing metric that uses feature importance weights to measure the coverage of the test set and facilitates the generation of additional test cases targeting higher weights’ features. Evaluations were conducted to compare the initial and final coverage of the proposed weighting approach with normal BN-based feature coverage. The testing coverage experiments indicated that the proposed weight metrics achieved higher coverage compared to the original feature metrics while maintaining the effectiveness of finding adversarial samples during the test case generation process.