arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.10027cs.CVcs.LG
收藏

神经元覆盖是否需要使人检测更鲁棒?

Is Neuron Coverage Needed to Make Person Detection More Robust?

FZI Research Center for Information Technology(FZI信息技术研究中心)

Svetlana Pavlitskaya, Şiyar Yıkmış, J. Marius Zöllner

摘要:

深度神经网络(DNN)在自动驾驶等安全关键领域的应用越来越多,这就需要对其进行系统测试。覆盖引导测试(CGT)是一种根据预定义的覆盖度量应用突变或模糊化来发现导致错误行为的输入的方法。随着神经元覆盖度量的引入,CGT最近也被应用于DNN。在这项工作中,我们将CGT应用于拥挤场景中的人员检测任务。拟议的管道使用YOLOv 3进行人员检测,包括通过采样和突变发现DNN错误,以及随后对更新的训练集进行DNN再训练。要成为一个bug,我们需要一个变异的图像与一个干净的输入相比会导致显著的性能下降。根据CGT,我们还考虑了在bug定义中增加覆盖率的额外要求。为了探索几种类型的鲁棒性,我们的方法包括自然图像变换,腐败和Daedalus攻击生成的对抗性示例。该框架已经发现了数千种不正确的DNN行为。对于不同的鲁棒性类型,再训练模型的mAP性能的相对变化平均在26.21%~ 64.24%之间。然而,我们没有发现任何证据表明,调查的覆盖率指标可以有利地用于提高鲁棒性。

英文摘要:

The growing use of deep neural networks (DNNs) in safety- and security-critical areas like autonomous driving raises the need for their systematic testing. Coverage-guided testing (CGT) is an approach that applies mutation or fuzzing according to a predefined coverage metric to find inputs that cause misbehavior. With the introduction of a neuron coverage metric, CGT has also recently been applied to DNNs. In this work, we apply CGT to the task of person detection in crowded scenes. The proposed pipeline uses YOLOv3 for person detection and includes finding DNN bugs via sampling and mutation, and subsequent DNN retraining on the updated training set. To be a bug, we require a mutated image to cause a significant performance drop compared to a clean input. In accordance with the CGT, we also consider an additional requirement of increased coverage in the bug definition. In order to explore several types of robustness, our approach includes natural image transformations, corruptions, and adversarial examples generated with the Daedalus attack. The proposed framework has uncovered several thousand cases of incorrect DNN behavior. The relative change in mAP performance of the retrained models reached on average between 26.21\% and 64.24\% for different robustness types. However, we have found no evidence that the investigated coverage metrics can be advantageously used to improve robustness.

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。

↑