A Real-Time Defense Against Object Vanishing Adversarial Patch Attacks for Object Detection in Autonomous Vehicles
Autonomous vehicles (AVs) increasingly use DNN-based object detection models in vision-based perception. Correct detection and classification of obstacles is critical to ensure safe, trustworthy driving decisions. Adversarial patches aim to fool a DNN with intentionally generated patterns concentrated in a localized region of an image. In particular, object vanishing patch attacks can cause object detection models to fail to detect most or all objects in a scene, posing a significant practical threat to AVs. This work proposes ADAV (Adversarial Defense for Autonomous Vehicles), a novel defense methodology against object vanishing patch attacks specifically designed for autonomous vehicles. Unlike existing defense methods which have high latency or are designed for static images, ADAV runs in real-time and leverages contextual information from prior frames in an AV's video feed. ADAV checks if the object detector's output for the target frame is temporally consistent with the output from a previous reference frame to detect the presence of a patch. If the presence of a patch is detected, ADAV uses gradient-based attribution to localize adversarial pixels that break temporal consistency. This two stage procedure allows ADAV to efficiently process clean inputs, and both stages are optimized to be low latency. ADAV is evaluated using real-world driving data from the Berkeley Deep Drive BDD100K dataset, and demonstrates high adversarial and clean performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial DefenseAutonomous VehiclesObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectors
Deep neural networks (DNNs) have revolutionized the field of computer vision like object detection with their unparalleled performance. However, existing research has shown that DNNs are vulnerable to adversarial attacks…
object-detectionObject DetectionPrediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks
High-performance Deep Neural Networks (DNNs) are increasingly deployed in many real-world applications e.g., cloud prediction APIs. Recent advances in model functionality stealing attacks via black-box access (i.e., inpu…
Autonomous VehiclesPredictionA 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 DefenseBackdoor 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 LearningTest-Time Backdoor Detection for Object Detection Models
Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. Detecting poisoned samples (i.e., those co…
image-classificationImage ClassificationObjectobject-detection+1