NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors
Ziqi Zhou, Bowen Li, Yufei Song, Zhifei Yu, Shengshan Hu, Wei Wan, Leo, Yu Zhang, Dezhong Yao, Hai Jin

TL;DR
NumbOD introduces a model-agnostic spatial-frequency fusion attack that effectively disrupts various object detectors by manipulating high-frequency image components and output features, revealing their vulnerabilities.
Contribution
It proposes a novel, scalable attack method that does not rely on internal model structures, utilizing spatial-frequency fusion and feature-based targeting for efficient adversarial attacks.
Findings
Achieves high attack success across nine object detectors
Demonstrates high stealthiness and efficiency in attacks
Effective on multiple datasets
Abstract
With the advancement of deep learning, object detectors (ODs) with various architectures have achieved significant success in complex scenarios like autonomous driving. Previous adversarial attacks against ODs have been focused on designing customized attacks targeting their specific structures (e.g., NMS and RPN), yielding some results but simultaneously constraining their scalability. Moreover, most efforts against ODs stem from image-level attacks originally designed for classification tasks, resulting in redundant computations and disturbances in object-irrelevant areas (e.g., background). Consequently, how to design a model-agnostic efficient attack to comprehensively evaluate the vulnerabilities of ODs remains challenging and unresolved. In this paper, we propose NumbOD, a brand-new spatial-frequency fusion attack against various ODs, aimed at disrupting object detection within…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRadiation Detection and Scintillator Technologies · Biometric Identification and Security · Brain Tumor Detection and Classification
MethodsSoftmax · Attention Is All You Need · Focus
