Understanding Object Detection Through An Adversarial Lens
Deep neural networks based object detection models have revolutionized computer vision and fueled the development of a wide range of visual recognition applications. However, recent studies have revealed that deep object detectors can be compromised under adversarial attacks, causing a victim detector to detect no object, fake objects, or mislabeled objects. With object detection being used pervasively in many security-critical applications, such as autonomous vehicles and smart cities, we argue that a holistic approach for an in-depth understanding of adversarial attacks and vulnerabilities of deep object detection systems is of utmost importance for the research community to develop robust defense mechanisms. This paper presents a framework for analyzing and evaluating vulnerabilities of the state-of-the-art object detectors under an adversarial lens, aiming to analyze and demystify the attack strategies, adverse effects, and costs, as well as the cross-model and cross-resolution transferability of attacks. Using a set of quantitative metrics, extensive experiments are performed on six representative deep object detectors from three popular families (YOLOv3, SSD, and Faster R-CNN) with two benchmark datasets (PASCAL VOC and MS COCO). We demonstrate that the proposed framework can serve as a methodical benchmark for analyzing adversarial behaviors and risks in real-time object detection systems. We conjecture that this framework can also serve as a tool to assess the security risks and the adversarial robustness of deep object detectors to be deployed in real-world applications.
Code (1)
Tasks
Adversarial RobustnessAutonomous VehiclesObjectobject-detectionObject DetectionReal-Time Object DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks
Scene understanding is crucial for autonomous systems which intend to operate in the real world. Single task vision networks extract information only based on some aspects of the scene. In multi-task learning (MTL), on t…
Depth EstimationDepth PredictionInstance SegmentationMonocular Depth Estimation+5Adversarial Camera Patch: An Effective and Robust Physical-World Attack on Object Detectors
Nowadays, the susceptibility of deep neural networks (DNNs) has garnered significant attention. Researchers are exploring patch-based physical attacks, yet traditional approaches, while effective, often result in conspic…
Scratched Lenses, Shifted Depth: Passive Camera-Side Optical Attacks
Physical adversarial attacks on vision systems are typically studied through scene manipulation, such as adversarial patches or projections, where the adversary controls what the camera observes. Camera-side attacks usin…
Monocular 3D Object DetectionMonocular Depth EstimationStability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNs
In this paper we construct and theoretically analyse group equivariant convolutional kernel networks (CKNs) which are useful in understanding the geometry of (equivariant) CNNs through the lens of reproducing kernel Hilb…
Representation LearningFeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Features
Although the remarkable performance of deep neural networks (DNNs) in image classification, their vulnerability to adversarial attacks remains a critical challenge. Most existing detection methods rely on complex and poo…
Computational EfficiencyImage ClassificationAdversarial Defense