在物体框外植入隐蔽触发器，骗过目标检测模型。
Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors
- 在物体边界框外添加隐蔽触发器，避免引起注意。
- 新方法在数字和物理场景中均实现高攻击成功率。
- 适合研究对抗样本防御或安全测试的开发者。
近年来，针对基于深度神经网络（DNN）的目标检测系统，对抗鲁棒性研究已成为关键领域。传统物理攻击方法如对抗补丁和纹理篡改，直接修改物体表面，虽有效但易被察觉。为此，本文提出一种更隐蔽的方法：在物体边界框外施加不易察觉的对抗触发器，使模型无法检测到该物体。我们进一步引入特征引导（FG）技术与通用自动PGD（UAPGD）优化策略，生成高质量触发器。通过大量实证测试验证了该方法的有效性，在数字与物理环境中均表现出优异性能。代码与视频将公开于：https://github.com/linToTao/Out-of-bbox-attack。
原文摘要 · Abstract (English)
In recent years, the study of adversarial robustness in object detection systems, particularly those based on deep neural networks (DNNs), has become a pivotal area of research. Traditional physical attacks targeting object detectors, such as adversarial patches and texture manipulations, directly manipulate the surface of the object. While these methods are effective, their overt manipulation of objects may draw attention in real-world applications. To address this, this paper introduces a more subtle approach: an inconspicuous adversarial trigger that operates outside the bounding boxes, rendering the object undetectable to the model. We further enhance this approach by proposing the Feature Guidance (FG) technique and the Universal Auto-PGD (UAPGD) optimization strategy for crafting high-quality triggers. The effectiveness of our method is validated through extensive empirical testing, demonstrating its high performance in both digital and physical environments. The code and video will be available at: https://github.com/linToTao/Out-of-bbox-attack.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。