CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild
In this paper, we conduct an intriguing experimental study about the physical adversarial attack on object detectors in the wild. In particular, we learn a camouflage pattern to hide vehicles from being detected by state-of-the-art convolutional neural network based detectors. Our approach alternates between two threads. In the first, we train a neural approximation function to imitate how a simulator applies a camouflage to vehicles and how a vehicle detector performs given images of the camouflaged vehicles. In the second, we minimize the approximated detection score by searching for the optimal camouflage. Experiments show that the learned camouflage can not only hide a vehicle from the image-based detectors under many test cases but also generalizes to different environments, vehicles, and object detectors.
Code (1)
Tasks
Adversarial AttackObjectSimilar Papers 제목 키워드 기반
Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World
Deep learning models are vulnerable to adversarial examples. As a more threatening type for practical deep learning systems, physical adversarial examples have received extensive research attention in recent years. Howev…
FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack
Physical adversarial attacks in object detection have attracted increasing attention. However, most previous works focus on hiding the objects from the detector by generating an individual adversarial patch, which only c…
Adversarial Attackobject-detectionObject DetectionCCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection
Deep neural network based object detection hasbecome the cornerstone of many real-world applications. Alongwith this success comes concerns about its vulnerability tomalicious attacks. To gain more insight into this issu…
Objectobject-detectionObject DetectionComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages
As 3D Gaussian Splatting (3DGS) gains rapid adoption in safety-critical tasks for efficient novel-view synthesis from static images, how might an adversary tamper images to cause harm? We introduce ComplicitSplat, the fi…
Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
Graph Neural Networks (GNNs) have been widely applied to fraud detection problems in recent years, revealing the suspiciousness of nodes by aggregating their neighborhood information via different relations. However, few…
Anomaly DetectionFraud DetectionGraph MiningGraph Neural Network+2