arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.05334cs.CVcs.AIcs.CRcs.LG
收藏

通过复杂目标场景的3D建模增强真实世界的对抗补丁

Enhancing Real-World Adversarial Patches through 3D Modeling of Complex Target Scenes

Ben-Gurion University of the Negev(内盖夫本-古里安大学)

Yael Mathov, Lior Rokach, Yuval Elovici

摘要:

对抗性示例已被证明是对深度学习模型的一个令人担忧的威胁,特别是在图像领域。然而,尽管许多研究都研究了现实世界中的对抗性例子,但大多数研究都依赖于攻击场景的2D照片。因此,所提出的攻击在具有3D对象或不同条件的现实环境中实施时可能具有有限的有效性。很少有关于使用3D对象的对抗性学习的研究,在许多情况下,其他研究人员无法复制真实世界的评估过程。在这项研究中,我们提出了一个框架,使用3D建模工艺对抗补丁现有的现实世界的场景。我们的方法使用3D数字近似的场景作为模拟现实世界。通过在数字场景中添加和操作任何元素的能力,我们的框架使攻击者能够提高对抗补丁在现实世界中的影响。我们使用该框架为日常场景创建一个补丁,并使用一个新颖的评估过程来评估其性能,该过程确保我们的结果在数字空间和现实世界中都是可复制的。我们的评估结果表明,该框架可以生成对抗补丁,在现实世界中的不同设置是强大的。

英文摘要:

Adversarial examples have proven to be a concerning threat to deep learning models, particularly in the image domain. However, while many studies have examined adversarial examples in the real world, most of them relied on 2D photos of the attack scene. As a result, the attacks proposed may have limited effectiveness when implemented in realistic environments with 3D objects or varied conditions. There are few studies on adversarial learning that use 3D objects, and in many cases, other researchers are unable to replicate the real-world evaluation process. In this study, we present a framework that uses 3D modeling to craft adversarial patches for an existing real-world scene. Our approach uses a 3D digital approximation of the scene as a simulation of the real world. With the ability to add and manipulate any element in the digital scene, our framework enables the attacker to improve the adversarial patch's impact in real-world settings. We use the framework to create a patch for an everyday scene and evaluate its performance using a novel evaluation process that ensures that our results are reproducible in both the digital space and the real world. Our evaluation results show that the framework can generate adversarial patches that are robust to different settings in the real world.

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。

↑