Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examples

• URL: http://arxiv.org/abs/2503.21164v1
• Date: Thu, 27 Mar 2025 05:19:41 GMT
• Title: Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examples
• Authors: Samra Irshad, Seungkyu Lee, Nassir Navab, Hong Joo Lee, Seong Tae Kim,
• Abstract summary: AdvWT is a new class of physical-world adversarial examples.<n>It draws inspiration from the naturally occurring phenomenon of wear and tear'<n>We show that AdvWT effectively misleads in both digital and physical domains.
• Score: 44.16359029935054
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The presence of adversarial examples in the physical world poses significant challenges to the deployment of Deep Neural Networks in safety-critical applications such as autonomous driving. Most existing methods for crafting physical-world adversarial examples are ad-hoc, relying on temporary modifications like shadows, laser beams, or stickers that are tailored to specific scenarios. In this paper, we introduce a new class of physical-world adversarial examples, AdvWT, which draws inspiration from the naturally occurring phenomenon of `wear and tear', an inherent property of physical objects. Unlike manually crafted perturbations, `wear and tear' emerges organically over time due to environmental degradation, as seen in the gradual deterioration of outdoor signboards. To achieve this, AdvWT follows a two-step approach. First, a GAN-based, unsupervised image-to-image translation network is employed to model these naturally occurring damages, particularly in the context of outdoor signboards. The translation network encodes the characteristics of damaged signs into a latent `damage style code'. In the second step, we introduce adversarial perturbations into the style code, strategically optimizing its transformation process. This manipulation subtly alters the damage style representation, guiding the network to generate adversarial images where the appearance of damages remains perceptually realistic, while simultaneously ensuring their effectiveness in misleading neural networks. Through comprehensive experiments on two traffic sign datasets, we show that AdvWT effectively misleads DNNs in both digital and physical domains. AdvWT achieves an effective attack success rate, greater robustness, and a more natural appearance compared to existing physical-world adversarial examples. Additionally, integrating AdvWT into training enhances a model's generalizability to real-world damaged signs.

Related papers

• Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers [1.1187085721899017]
  We study the sources of known representation vulnerabilities of vision transformers (ViT), where perceptually identical images can have very different representations.<n>We develop NeuroShield-ViT, a novel defense mechanism that strategically neutralizes vulnerable neurons in earlier layers to prevent the cascade of adversarial effects.<n>Our results shed new light on how adversarial effects propagate through ViT layers, while providing a promising approach to enhance the robustness of vision transformers against adversarial attacks.
  arXiv  Detail & Related papers  (2025-02-07T05:58:16Z)
• Imperceptible Adversarial Examples in the Physical World [10.981325924844167]
  We make adversarial examples imperceptible in the physical world using a straight-through estimator (STE, a.k.a. BPDA) Our differentiable rendering extension to STE also enables imperceptible adversarial patches in the physical world. To the best of our knowledge, this is the first work demonstrating imperceptible adversarial examples bounded by small norms in the physical world.
  arXiv  Detail & Related papers  (2024-11-25T18:02:23Z)
• F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns [74.03108122774098]
  Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical diagnosis. We propose a Feature-Focusing Adversarial Training (F$2$AT) which enforces the model to focus on the core features from natural patterns.
  arXiv  Detail & Related papers  (2023-10-23T04:31:42Z)
• Why Don't You Clean Your Glasses? Perception Attacks with Dynamic Optical Perturbations [17.761200546223442]
  Adapting adversarial attacks to the physical world is desirable for the attacker, as this removes the need to compromise digital systems. We present EvilEye, a man-in-the-middle perception attack that leverages transparent displays to generate dynamic physical adversarial examples.
  arXiv  Detail & Related papers  (2023-07-24T21:16:38Z)
• Mitigating Adversarial Attacks in Deepfake Detection: An Exploration of Perturbation and AI Techniques [1.0718756132502771]
  adversarial examples are subtle perturbations artfully injected into clean images or videos. Deepfakes have emerged as a potent tool to manipulate public opinion and tarnish the reputations of public figures. This article delves into the multifaceted world of adversarial examples, elucidating the underlying principles behind their capacity to deceive deep learning algorithms.
  arXiv  Detail & Related papers  (2023-02-22T23:48:19Z)
• Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon [79.33449311057088]
  We study a new type of optical adversarial examples, in which the perturbations are generated by a very common natural phenomenon, shadow. We extensively evaluate the effectiveness of this new attack on both simulated and real-world environments.
  arXiv  Detail & Related papers  (2022-03-08T02:40:18Z)
• On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving [59.33715889581687]
  The existence of real-world adversarial examples (commonly in the form of patches) poses a serious threat for the use of deep learning models in safety-critical computer vision tasks. This paper presents an evaluation of the robustness of semantic segmentation models when attacked with different types of adversarial patches. A novel loss function is proposed to improve the capabilities of attackers in inducing a misclassification of pixels.
  arXiv  Detail & Related papers  (2022-01-05T22:33:43Z)
• Real-World Adversarial Examples involving Makeup Application [58.731070632586594]
  We propose a physical adversarial attack with the use of full-face makeup. Our attack can effectively overcome manual errors in makeup application, such as color and position-related errors.
  arXiv  Detail & Related papers  (2021-09-04T05:29:28Z)
• Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks [62.87459235819762]
  In a real-world scenario like autonomous driving, more attention should be devoted to real-world adversarial examples (RWAEs) This paper presents an in-depth evaluation of the robustness of popular SS models by testing the effects of both digital and real-world adversarial patches.
  arXiv  Detail & Related papers  (2021-08-13T11:49:09Z)
• Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles [40.57099683047126]
  We propose a novel approach to craft and camouflage physical-world adversarial examples into natural styles that appear legitimate to human observers. emphAdvCam can also be used to protect private information from being detected by deep learning systems.
  arXiv  Detail & Related papers  (2020-03-08T07:22:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.