Test-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 containing triggers) at test time can prevent backdoor activation. However, unlike image classification tasks, the unique characteristics of object detection -- particularly its output of numerous objects -- pose fresh challenges for backdoor detection. The complex attack effects (e.g., "ghost" object emergence or "vanishing" object) further render current defenses fundamentally inadequate. To this end, we design TRAnsformation Consistency Evaluation (TRACE), a brand-new method for detecting poisoned samples at test time in object detection. Our journey begins with two intriguing observations: (1) poisoned samples exhibit significantly more consistent detection results than clean ones across varied backgrounds. (2) clean samples show higher detection consistency when introduced to different focal information. Based on these phenomena, TRACE applies foreground and background transformations to each test sample, then assesses transformation consistency by calculating the variance in objects confidences. TRACE achieves black-box, universal backdoor detection, with extensive experiments showing a 30% improvement in AUROC over state-of-the-art defenses and resistance to adaptive attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
BadDet: Backdoor Attacks on Object Detection
Deep learning models have been deployed in numerous real-world applications such as autonomous driving and surveillance. However, these models are vulnerable in adversarial environments. Backdoor attack is emerging as a …
Autonomous DrivingBackdoor Attackimage-classificationImage Classification+3Mask-based Invisible Backdoor Attacks on Object Detection
Deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to…
Autonomous DrivingBackdoor Attackimage-classificationObject DetectionAttacking by Aligning: Clean-Label Backdoor Attacks on Object Detection
Deep neural networks (DNNs) have shown unprecedented success in object detection tasks. However, it was also discovered that DNNs are vulnerable to multiple kinds of attacks, including Backdoor Attacks. Through the attac…
Autonomous DrivingBackdoor Attackimage-classificationImage Classification+3Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis
Object detection models, widely used in security-critical applications, are vulnerable to backdoor attacks that cause targeted misclassifications when triggered by specific patterns. Existing backdoor defense techniques,…
backdoor defenseObjectobject-detectionObject Detection+2Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techn…
Autonomous DrivingBackdoor AttackObjectobject-detection+1