On Physical Adversarial Patches for Object Detection

Abstract

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 the objects being misclassified or avoiding detection, we show that a properly designed patch can suppress virtually all the detected objects in the image. That is, we can place the patch anywhere in the image, causing all existing objects in the image to be missed entirely by the detector, even those far away from the patch itself. This in turn opens up new lines of physical attacks against object detection systems, which require no modification of the objects in a scene. A demo of the system can be found at https://youtu.be/WXnQjbZ1e7Y.

References in corpus (1)

• YOLOv3: An Incremental Improvement

Cited by in corpus (29)

• Blind Backdoors in Deep Learning Models
• Adversarial Training against Location-Optimized Adversarial Patches
• Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses
• On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
• Towards robust sensing for Autonomous Vehicles: An adversarial perspective
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images
• Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patches
• Unadversarial Examples: Designing Objects for Robust Vision
• Efficient Certified Defenses Against Patch Attacks on Image Classifiers
• Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Frame
• DPAttack: Diffused Patch Attacks against Universal Object Detection
• Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis
• Does enhanced shape bias improve neural network robustness to common corruptions?
• ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
• Adversarial Patch Camouflage against Aerial Detection
• Design and Interpretation of Universal Adversarial Patches in Face Detection
• Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications
• Adversarial Detection: Attacking Object Detection in Real Time
• Mixup Regularization for Region Proposal based Object Detectors
• DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks
• Meta Adversarial Training against Universal Patches
• Adversarial Attacks on Optimization based Planners
• Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions
• Detecting Adversarial Patches with Class Conditional Reconstruction Networks
• CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection
• Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs
• Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devices
• Developing and Defeating Adversarial Examples