NAPGuard: Towards Detecting Naturalistic Adversarial Patches
Recently the emergence of naturalistic adversarial patch (NAP) which possesses a deceptive appearance and various representations underscores the necessity of developing robust detection strategies. However existing approaches fail to differentiate the deep-seated natures in adversarial patches i.e. aggressiveness and naturalness leading to unsatisfactory precision and generalization against NAPs. To tackle this issue we propose NAPGuard to provide strong detection capability against NAPs via the elaborated critical feature modulation framework. For improving precision we propose the aggressive feature aligned learning to enhance the model's capability in capturing accurate aggressive patterns. Considering the challenge of inaccurate model learning caused by deceptive appearance we align the aggressive features by the proposed pattern alignment loss during training. Since the model could learn more accurate aggressive patterns it is able to detect deceptive patches more precisely. To enhance generalization we design the natural feature suppressed inference to universally mitigate the disturbance from different NAPs. Since various representations arise in diverse disturbing forms to hinder generalization we suppress the natural features in a unified approach via the feature shield module. Therefore the models could recognize NAPs within less disturbance and activate the generalized detection ability. Extensive experiments show that our method surpasses state-of-the-art methods by large margins in detecting NAPs (improve 60.24% AP@0.5 on average).
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection
Standard approaches for adversarial patch generation lead to noisy conspicuous patterns, which are easily recognizable by humans. Recent research has proposed several approaches to generate naturalistic patches using gen…
object-detectionObject DetectionDiffPatch: Generating Customizable Adversarial Patches using Diffusion Model
Physical adversarial patches printed on clothing can easily allow individuals to evade person detectors. However, most existing adversarial patch generation methods prioritize attack effectiveness over stealthiness, resu…
modelDiffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector
Many physical adversarial patch generation methods are widely proposed to protect personal privacy from malicious monitoring using object detectors. However, they usually fail to generate satisfactory patch images in ter…
Jedi: Entropy-based Localization and Removal of Adversarial Patches
Real-world adversarial physical patches were shown to be successful in compromising state-of-the-art models in a variety of computer vision applications. Existing defenses that are based on either input gradient or featu…
Naturalistic Physical Adversarial Patch for Object Detectors
Most prior works on physical adversarial attacks mainly focus on the attack performance but seldom enforce any restrictions over the appearance of the generated adversarial patches. This leads to conspicuous and atte…
Generative Adversarial NetworkObject