Can I read Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World on EtoBox?

Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World by Ma, Hua; Abuadbba, Alsharif; Gao, Yansong; Kim, Hyoungshick; Nepal, Surya is a scholarly article available to read on EtoBox.

What is Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World about?

The exploration of backdoor vulnerabilities in object detectors, particularly in real-world scenarios, remains limited. A significant challenge lies in the absence of a natural physical backdoor dataset, and constructing such a dataset is both time- and labor-intensive. In this work, we address this gap by creating a large-scale dataset comprising approximately 11,800 images/frames with annotations featuring natural objects (e.g., T-shirts and hats) as triggers to incur cloaking adversarial effects in diverse real-world scenarios. This dataset is tailored for the study of physical backdoors in object detectors. Leveraging this dataset, we conduct a comprehensive evaluation of an insidious cloaking backdoor effect against object detectors, wherein the bounding box around a person vanishes when the individual is near a natural object (e.g., a commonly available T-shirt) in front of the detector. Our evaluations encompass three prevalent attack surfaces: data outsourcing, model outsourcing, and the use of pretrained models. The cloaking effect is successfully implanted in object detectors across all three attack surfaces. We extensively evaluate four popular object detection algorithm

Author

Ma, Hua; Abuadbba, Alsharif; Gao, Yansong; Kim, Hyoungshick; Nepal, Surya

Published

2025

Language

EN