paper-with-me

Papers

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, Ziqi Zhou, Xianlong Wang, Yanjun Zhang, Chao Chen

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 techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: Sponge for triggering widespread misidentifications and Blinding for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement ($\sim$10\%-60\% absolute and $\sim$2-7$\times$ relative) in attack efficacy over state-of-the-art attacks.

📄 PDF Abstract BibTeX arXiv:2404.11357

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingBackdoor AttackObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World

2022-09-06 · Hua Ma, Yinshan Li, Yansong Gao, Zhi Zhang 외

Object detection is the foundation of various critical computer-vision tasks such as segmentation, object tracking, and event detection. To train an object detector with satisfactory accuracy, a large amount of data is r…

Event Detectionimage-classificationImage ClassificationObject+3

Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attacks

2020-04-26 · Kang Liu, Benjamin Tan, Gaurav Rajavendra Reddy, Siddharth Garg 외

Deep learning (DL) offers potential improvements throughout the CAD tool-flow, one promising application being lithographic hotspot detection. However, DL techniques have been shown to be especially vulnerable to inferen…

Data Augmentation

PhyLatent: Learning Dynamics-Relevant Representations for JEPA World Models

2026-08-06 · Xi Zeng, Haojie Ren, Ziying Song arxiv

We propose PhyLatent, a dynamics-relevant training objective for JointEmbedding Predictive Architecture (JEPA) world models. Our key observation is that preventing global latent collapse does not ensure that a representa…

Adversarial T-shirt! Evading Person Detectors in A Physical World

2019-10-18 · ECCV 2020 8 · Kaidi Xu, Gaoyuan Zhang, Sijia Liu, Quanfu Fan 외

It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decisionmakers by attaching adversarial patches to real objects. However, …

Physically Adversarial Infrared Patches with Learnable Shapes and Locations

2023-03-24 · CVPR 2023 1 · Wei Xingxing, Yu Jie, Huang Yao

Owing to the extensive application of infrared object detectors in the safety-critical tasks, it is necessary to evaluate their robustness against adversarial examples in the real world. However, current few physical inf…

Objectobject-detectionObject Detection