兴奋过度导致错误：基于可兴奋神经元的深度学习测试框架
Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neurons
摘要：
尽管深度神经网络（DNN）具有令人印象深刻的能力和出色的性能，但由于其频繁发生的错误行为，其安全问题引起了越来越多的公众关注。因此，在将DNN部署到实际应用之前，有必要对DNN进行系统的测试。现有的测试方法已经提供了基于神经元覆盖的细粒度度量，并提出了各种方法来改进这些度量。然而，已经逐渐认识到，较高的神经元覆盖率确实必然表示\textit{not}在识别导致错误的缺陷方面的更好的能力。此外，覆盖率引导的方法不能捕捉错误，由于错误的训练过程。因此，通过这些测试示例进行再训练来提高DNN的鲁棒性并不令人满意。为了应对这一挑战，我们引入了基于Shapley值的可兴奋神经元的概念，并为DNN设计了一个新的白盒测试框架，即DeepSensor。这是由我们的观察所激发的，即由于小扰动而对模型损失变化具有较大责任的神经元更可能与由于潜在缺陷而导致的不正确的角点情况相关。通过最大化模型各种错误行为的可兴奋神经元数量，DeepSensor可以生成测试示例，有效地触发更多由于对抗性输入、污染数据和不完整训练而导致的错误。在图像分类模型和说话人识别模型上进行的大量实验证明了DeepSensor的优越性。
英文摘要：
Despite impressive capabilities and outstanding performance, deep neural networks (DNNs) have captured increasing public concern about their security problems, due to their frequently occurred erroneous behaviors. Therefore, it is necessary to conduct a systematical testing for DNNs before they are deployed to real-world applications. Existing testing methods have provided fine-grained metrics based on neuron coverage and proposed various approaches to improve such metrics. However, it has been gradually realized that a higher neuron coverage does \textit{not} necessarily represent better capabilities in identifying defects that lead to errors. Besides, coverage-guided methods cannot hunt errors due to faulty training procedure. So the robustness improvement of DNNs via retraining by these testing examples are unsatisfactory. To address this challenge, we introduce the concept of excitable neurons based on Shapley value and design a novel white-box testing framework for DNNs, namely DeepSensor. It is motivated by our observation that neurons with larger responsibility towards model loss changes due to small perturbations are more likely related to incorrect corner cases due to potential defects. By maximizing the number of excitable neurons concerning various wrong behaviors of models, DeepSensor can generate testing examples that effectively trigger more errors due to adversarial inputs, polluted data and incomplete training. Extensive experiments implemented on both image classification models and speaker recognition models have demonstrated the superiority of DeepSensor.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
