You Cannot Easily Catch Me: A Low-Detectable Adversarial Patch for Object Detectors
Zijian Zhu, Hang Su, Chang Liu, Wenzhao Xiang, Shibao Zheng

TL;DR
This paper introduces a novel low-detectability adversarial patch that effectively fools object detectors while resisting detection, using geometric primitives and weighted loss functions, demonstrated on COCO and D2-City datasets.
Contribution
The paper proposes a new low-detectable adversarial patch for object detectors that is harder to identify and can bypass existing detection defenses.
Findings
LDAP effectively fools object detectors.
LDAP resists existing adversarial patch detectors.
Experimental validation on COCO and D2-City datasets shows strong attack performance.
Abstract
Blind spots or outright deceit can bedevil and deceive machine learning models. Unidentified objects such as digital "stickers," also known as adversarial patches, can fool facial recognition systems, surveillance systems and self-driving cars. Fortunately, most existing adversarial patches can be outwitted, disabled and rejected by a simple classification network called an adversarial patch detector, which distinguishes adversarial patches from original images. An object detector classifies and predicts the types of objects within an image, such as by distinguishing a motorcyclist from the motorcycle, while also localizing each object's placement within the image by "drawing" so-called bounding boxes around each object, once again separating the motorcyclist from the motorcycle. To train detectors even better, however, we need to keep subjecting them to confusing or deceitful…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Anomaly Detection Techniques and Applications · Advanced Neural Network Applications
