paper-with-me

Papers

Test-Time Backdoor Detection for Object Detection Models

2025-03-19 · CVPR 2025 1 · Hangtao Zhang, Yichen Wang, Shihui Yan, Chenyu Zhu, Ziqi Zhou, Linshan Hou, Shengshan Hu, Minghui Li, Yanjun Zhang, Leo Yu Zhang

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.

📄 PDF Abstract BibTeX arXiv:2503.15293

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationObjectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

BadDet: Backdoor Attacks on Object Detection

2022-05-28 · Shih-Han Chan, Yinpeng Dong, Jun Zhu, Xiaolu Zhang 외

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+3

Mask-based Invisible Backdoor Attacks on Object Detection

2024-03-20 · Jeongjin Shin

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 Detection

Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection

2023-07-19 · Yize Cheng, Wenbin Hu, Minhao Cheng

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+3

Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis

2024-09-24 · Xianda Zhang, Siyuan Liang

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+2

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

2024-04-17 · Hangtao Zhang, Shengshan Hu, Yichen Wang, Leo Yu Zhang 외

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