PADetBench: Towards Benchmarking Physical Attacks against Object Detection
Physical attacks against object detection have gained increasing attention due to their significant practical implications. However, conducting physical experiments is extremely time-consuming and labor-intensive. Moreover, physical dynamics and cross-domain transformation are challenging to strictly regulate in the real world, leading to unaligned evaluation and comparison, severely hindering the development of physically robust models. To accommodate these challenges, we explore utilizing realistic simulation to thoroughly and rigorously benchmark physical attacks with fairness under controlled physical dynamics and cross-domain transformation. This resolves the problem of capturing identical adversarial images that cannot be achieved in the real world. Our benchmark includes 20 physical attack methods, 48 object detectors, comprehensive physical dynamics, and evaluation metrics. We also provide end-to-end pipelines for dataset generation, detection, evaluation, and further analysis. In addition, we perform 8064 groups of evaluation based on our benchmark, which includes both overall evaluation and further detailed ablation studies for controlled physical dynamics. Through these experiments, we provide in-depth analyses of physical attack performance and physical adversarial robustness, draw valuable observations, and discuss potential directions for future research. Codebase: https://github.com/JiaweiLian/Benchmarking_Physical_Attack
Code (2)
Tasks
Adversarial RobustnessBenchmarkingDataset GenerationFairnessObjectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Revisiting Physically Realizable Adversarial Object Attack against LiDAR-based Detection: Clarifying Problem Formulation and Experimental Protocols
Adversarial robustness in LiDAR-based 3D object detection is a critical research area due to its widespread application in real-world scenarios. While many digital attacks manipulate point clouds or meshes, they often la…
Adversarial Robustness3D Object DetectionPoint CloudsBackdoor Attacks Against Deep Learning Systems in the Physical World
Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses…
Deep LearningTransfer LearningOn Physical Adversarial Patches for Object Detection
In this paper, we demonstrate a physical adversarial patch attack against object detectors, notably the YOLOv3 detector. Unlike previous work on physical object detection attacks, which required the patch to overlap with…
Objectobject-detectionObject DetectionDefenses Against Multi-Sticker Physical Domain Attacks on Classifiers
Recently, physical domain adversarial attacks have drawn significant attention from the machine learning community. One important attack proposed by Eykholt et al. can fool a classifier by placing black and white sticker…
A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical World
In recent years, adversarial attacks against deep learning-based object detectors in the physical world have attracted much attention. To defend against these attacks, researchers have proposed various defense methods ag…
Adversarial Defense