• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops >Fooling Automated Surveillance Cameras: Adversarial Patches to Attack Person Detection
【24h】

Fooling Automated Surveillance Cameras: Adversarial Patches to Attack Person Detection

机译：愚弄自动监控摄像头：对抗人员检测的对抗斑块

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Adversarial attacks on machine learning models have seen increasing interest in the past years. By making only subtle changes to the input of a convolutional neural network, the output of the network can be swayed to output a completely different result. The first attacks did this by changing pixel values of an input image slightly to fool a classifier to output the wrong class. Other approaches have tried to learn "patches" that can be applied to an object to fool detectors and classifiers. Some of these approaches have also shown that these attacks are feasible in the real-world, i.e. by modifying an object and filming it with a video camera. However, all of these approaches target classes that contain almost no intra-class variety (e.g. stop signs). The known structure of the object is then used to generate an adversarial patch on top of it. In this paper, we present an approach to generate adversarial patches to targets with lots of intra-class variety, namely persons. The goal is to generate a patch that is able successfully hide a person from a person detector. An attack that could for instance be used maliciously to circumvent surveillance systems, intruders can sneak around undetected by holding a small cardboard plate in front of their body aimed towards the surveilance camera. From our results we can see that our system is able significantly lower the accuracy of a person detector. Our approach also functions well in real-life scenarios where the patch is filmed by a camera. To the best of our knowledge we are the first to attempt this kind of attack on targets with a high level of intra-class variety like persons.
机译：对机器学习模型的对抗攻击已经看到过去几年越来越兴趣。通过对卷积神经网络的输入进行微妙的改变，可以摇曳网络的输出以输出完全不同的结果。通过稍微改变输入图像的像素值来愚弄分类器来输出错误类来执行第一次攻击。其他方法尝试学习可以应用于对象以愚弄探测器和分类器的“补丁”。其中一些方法还表明，这些攻击在现实世界中是可行的，即通过修改对象并用摄像机拍摄它。但是，所有这些方法都有几乎没有类内常量的目标类（例如，停止标志）。然后使用该物体的已知结构在其顶部产生对抗性贴剂。在本文中，我们提出了一种方法来产生对目标的侵犯斑块的侵害，包括众多繁殖，即人。目标是生成能够成功隐藏人检测器的人的补丁。一种攻击，可以恶意使用以避免监视系统，入侵者可以通过在身体前面的瞄准监控摄像机前面拿着一个小纸板板来潜入未被发现的。从我们的结果，我们可以看到我们的系统能够显着降低人探测器的准确性。我们的方法在现实生活场景中也运行良好，在贴片由相机拍摄的。据我们所知，我们是第一个尝试这种攻击对具有高水平类多样性的目标的攻击。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号