arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.00568cs.LGstat.ML
收藏

噪声和对抗攻击鲁棒性的权重映射层

Weight Map Layer for Noise and Adversarial Attack Robustness

University of Nottingham(诺丁汉大学)

Mohammed Amer, Tomás Maul

摘要:

卷积神经网络(CNN)以其在视觉相关任务中的良好性能和泛化能力而闻名,并且已经成为应用和研究领域的最新技术。然而,就像其他神经网络模型一样,它们容易受到噪声和对抗攻击的影响。对抗性防御旨在通过学习或架构修改来降低神经网络对对抗攻击的敏感性。我们提出了权重映射层(WM)作为CNN的通用架构,并表明它可以提高它们对噪声和对抗攻击的鲁棒性。我们进一步解释了两个WM变体的增强的鲁棒性来自于层所表现出的自适应激活方差放大。我们表明,WM层可以集成到按比例放大的模型中,以增加其噪声和对抗攻击的鲁棒性,同时在不同的数据集上实现可比的准确性水平。

英文摘要:

Convolutional neural networks (CNNs) are known for their good performance and generalization in vision-related tasks and have become state-of-the-art in both application and research-based domains. However, just like other neural network models, they suffer from a susceptibility to noise and adversarial attacks. An adversarial defence aims at reducing a neural network's susceptibility to adversarial attacks through learning or architectural modifications. We propose the weight map layer (WM) as a generic architectural addition to CNNs and show that it can increase their robustness to noise and adversarial attacks. We further explain that the enhanced robustness of the two WM variants results from the adaptive activation-variance amplification exhibited by the layer. We show that the WM layer can be integrated into scaled up models to increase their noise and adversarial attack robustness, while achieving comparable accuracy levels across different datasets.

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。

↑