.png){kind=icon}
Return
PATCHOUT: Adversarial Patch Detection and Localization using Semantic Consistency
.png){kind=icon}
OA
AI
DOI：10.1007/s11063-025-11775-5.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Computer vision systems are actively deployed in safety-critical applications such as autonomous vehicles. Real-world adversarial patches are capable of compromising the artificial intelligence (AI) systems with catastrophic outcomes. Existing defenses against patch attacks are based on identifying neurons, features, or gradients of high intensity. However, these defenses are vulnerable to weaker attacks that have less obvious attack signatures. In this paper, we propose the PATCHOUT framework that detects and locates adversarial patches using semantic consistency. Within patch detection, the key insight is that the top class predictions for an entity are semantically consistent for benign images, whereas they are inconsistent for attacked images. Within patch localization, it is observed that patches are semantically consistent with a coarse grained segmentation of the image. This allows the PATCHOUT framework to detect and remove adversarial patches using a class consistency checker as well as image segmentation, attribution analysis, and image restoration techniques. The experimental evaluation demonstrates that PATCHOUT can detect a broad range of adversarial patches with over 90% accuracy. The framework achieves 20% higher accuracy than other defenses. The framework is also evaluated against unseen attacks and adaptive attacks, reducing the success rate of adaptive attacks from 56% to 24%.
Keywords:
Adversarial Machine Learning
Adversarial Patch
Computer Vision
Artificial Intelligence
Journal
IF:
2.8
Papers:
174
Citations:
5.5K
Organization
Cited Papers
Projected Gradient Descent Algorithms for Solving Nonlinear Inverse Problems with Generative Priors
.png){kind=icon}
PREAI
ShareSave
ShareSaveShareSaveShareSave
View more