arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.05451cs.NEcs.AIcs.LG
收藏

NeuroEvolution方法的对抗鲁棒性评估

Adversarial Robustness Assessment of NeuroEvolution Approaches

University of Coimbra(科英布拉大学)

Inês Valentim, Nuno Lourenço, Nuno Antunes

摘要:

NeuroEvolution通过应用演化计算的技术自动生成人工神经网络。这些方法的主要目标是构建最大化预测性能的模型,有时还具有最小化计算复杂性的附加目标。虽然演化模型在性能方面取得了有竞争力的结果,但它们对对抗性示例的鲁棒性(这在安全关键场景中成为一个问题)受到了有限的关注。在本文中,我们评估了两个突出的神经进化方法在CIFAR-10图像分类任务中发现的模型的对抗鲁棒性:DENSER和NSGA-Net。由于模型是公开可用的,我们考虑白盒无目标攻击,其中扰动由L2或无穷范数约束。类似于手动设计的网络,我们的研究结果表明,当进化模型的攻击与迭代法,其准确性通常下降到,或接近于零下的距离度量。DENSER模型是这一趋势的例外,在L2威胁模型下显示出一定的抵抗力,即使在迭代攻击下,其准确率也仅从93.70%下降到18.10%。此外,我们还分析了在网络第一层之前对数据进行预处理的影响。我们的观察表明,其中一些技术可能会加剧添加到原始输入的扰动,从而可能损害鲁棒性。因此,在为容易发生对抗攻击的应用程序自动设计网络时,不应忽略这种选择。

英文摘要:

NeuroEvolution automates the generation of Artificial Neural Networks through the application of techniques from Evolutionary Computation. The main goal of these approaches is to build models that maximize predictive performance, sometimes with an additional objective of minimizing computational complexity. Although the evolved models achieve competitive results performance-wise, their robustness to adversarial examples, which becomes a concern in security-critical scenarios, has received limited attention. In this paper, we evaluate the adversarial robustness of models found by two prominent NeuroEvolution approaches on the CIFAR-10 image classification task: DENSER and NSGA-Net. Since the models are publicly available, we consider white-box untargeted attacks, where the perturbations are bounded by either the L2 or the Linfinity-norm. Similarly to manually-designed networks, our results show that when the evolved models are attacked with iterative methods, their accuracy usually drops to, or close to, zero under both distance metrics. The DENSER model is an exception to this trend, showing some resistance under the L2 threat model, where its accuracy only drops from 93.70% to 18.10% even with iterative attacks. Additionally, we analyzed the impact of pre-processing applied to the data before the first layer of the network. Our observations suggest that some of these techniques can exacerbate the perturbations added to the original inputs, potentially harming robustness. Thus, this choice should not be neglected when automatically designing networks for applications where adversarial attacks are prone to occur.

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。

↑