arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15290cs.CRcs.LG
收藏

基于数据增强的神经网络对抗攻击防御方法

A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks

University of California San Diego(加州大学圣迭戈分校);Telecom Paris(巴黎电信学院);Institut Polytechnique de Paris(巴黎综合理工学院);Columbia University(哥伦比亚大学)

Yi Zeng, Han Qiu, Gerard Memmi, Meikang Qiu

摘要:

众所周知,计算机视觉(CV)中的深度神经网络(DNN)易受对抗性示例(AE)的影响,即恶意添加的不可感知的扰动会导致错误的分类结果。这种可变性已经成为现实生活中配备DNN作为核心组件的系统的潜在风险。人们已经在研究如何保护DNN模型不被AE处理方面做出了许多努力。然而,以前的工作还没有能够有效地降低新型对抗攻击造成的影响并同时兼容现实生活的限制。在本文中,我们专注于开发一个轻量级的防御方法,可以有效地无效与现实生活中的约束兼容的全白盒对抗攻击。从基本的仿射变换,我们集成了三个变换与随机系数,微调尊重的变化量的捍卫样本。与过去两年在顶级AI会议上发表的4种最先进的防御方法相比,我们的方法表现出了出色的鲁棒性和效率。值得强调的是,我们的模型可以承受高级自适应攻击,即50轮的BPDA,并且仍然帮助目标模型保持80%左右的准确率,同时将攻击成功率限制在几乎为零。

英文摘要:

Deep Neural Networks (DNNs) in Computer Vision (CV) are well-known to be vulnerable to Adversarial Examples (AEs), namely imperceptible perturbations added maliciously to cause wrong classification results. Such variability has been a potential risk for systems in real-life equipped DNNs as core components. Numerous efforts have been put into research on how to protect DNN models from being tackled by AEs. However, no previous work can efficiently reduce the effects caused by novel adversarial attacks and be compatible with real-life constraints at the same time. In this paper, we focus on developing a lightweight defense method that can efficiently invalidate full whitebox adversarial attacks with the compatibility of real-life constraints. From basic affine transformations, we integrate three transformations with randomized coefficients that fine-tuned respecting the amount of change to the defended sample. Comparing to 4 state-of-art defense methods published in top-tier AI conferences in the past two years, our method demonstrates outstanding robustness and efficiency. It is worth highlighting that, our model can withstand advanced adaptive attack, namely BPDA with 50 rounds, and still helps the target model maintain an accuracy around 80 %, meanwhile constraining the attack success rate to almost zero.

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。

↑