arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.08945cs.CRcs.LG
收藏

对深度学习模型的鲁棒物理世界攻击

Robust Physical-World Attacks on Deep Learning Models

University of Michigan(密歇根大学);University of Washington(华盛顿大学);University of California, Berkeley(加利福尼亚大学伯克利分校);Samsung Research America(三星美国研究院);Stony Brook University(石溪大学)

Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Amir Rahmati, Chaowei Xiao, Atul Prakash, Tadayoshi Kohno, Dawn Song

摘要:

最近的研究表明,最先进的深度神经网络(DNN)容易受到对抗性示例的影响,这是由于输入中添加了小幅度的扰动。鉴于新兴的物理系统在安全关键情况下使用DNN,对抗性示例可能会误导这些系统并导致危险情况。因此,理解物理世界中的对抗性示例是开发弹性学习算法的重要一步。我们提出了一个通用的攻击算法,鲁棒物理扰动(RP 2),在不同的物理条件下产生鲁棒的视觉对抗扰动。使用道路标志分类的真实案例,我们表明使用RP 2生成的对抗性示例在各种环境条件下(包括视点)实现了针对物理世界中标准架构道路标志分类器的高目标误分类率。由于目前缺乏标准化的测试方法,我们提出了一个两阶段的评估方法,强大的物理对抗的例子,包括实验室和现场测试。使用这种方法,我们评估了物理对抗操作对真实对象的有效性。在只有黑白贴纸的形式的扰动下,我们攻击了一个真正的停车标志,导致在实验室设置中获得的100%的图像中以及在移动车辆上获得的84.8%的捕获视频帧中(现场测试)的目标分类器的目标误分类。

英文摘要:

Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input. Given that that emerging physical systems are using DNNs in safety-critical situations, adversarial examples could mislead these systems and cause dangerous situations.Therefore, understanding adversarial examples in the physical world is an important step towards developing resilient learning algorithms. We propose a general attack algorithm,Robust Physical Perturbations (RP2), to generate robust visual adversarial perturbations under different physical conditions. Using the real-world case of road sign classification, we show that adversarial examples generated using RP2 achieve high targeted misclassification rates against standard-architecture road sign classifiers in the physical world under various environmental conditions, including viewpoints. Due to the current lack of a standardized testing method, we propose a two-stage evaluation methodology for robust physical adversarial examples consisting of lab and field tests. Using this methodology, we evaluate the efficacy of physical adversarial manipulations on real objects. Witha perturbation in the form of only black and white stickers,we attack a real stop sign, causing targeted misclassification in 100% of the images obtained in lab settings, and in 84.8%of the captured video frames obtained on a moving vehicle(field test) for the target classifier.

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。

↑