Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World

TL;DR

This paper introduces a large-scale real-world dataset and evaluates the robustness of cloaking backdoor attacks on object detectors, revealing their high success rate and stealthiness across multiple scenarios and algorithms.

Contribution

The work provides the first large-scale physical backdoor dataset for object detectors and offers a comprehensive evaluation of cloaking backdoor effectiveness in real-world conditions.

Findings

Cloaking backdoors achieve near 100% attack success rate in most scenarios.

Backdoor models maintain high accuracy on clean data, making detection difficult.

Backdoor effectiveness is robust against movement, distance, angle, deformation, and lighting.

Abstract

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 algorithms (anchor-based Yolo-V3, Yolo-V4, Faster R-CNN, and anchor-free CenterNet) using 19 videos (totaling approximately 11,800 frames) in real-world scenarios. Our results demonstrate that the backdoor attack exhibits remarkable robustness against various factors, including movement, distance, angle, non-rigid deformation, and lighting. In data and model outsourcing scenarios, the attack success rate (ASR) in most videos reaches 100% or near it, while the clean data accuracy of the backdoored model remains indistinguishable from that of the clean model, making it impossible to detect backdoor behavior through a validation set.