paper-with-me

Papers

Transient Adversarial 3D Projection Attacks on Object Detection in Autonomous Driving

2024-09-25 · Ce Zhou, Qiben Yan, Sijia Liu

Object detection is a crucial task in autonomous driving. While existing research has proposed various attacks on object detection, such as those using adversarial patches or stickers, the exploration of projection attacks on 3D surfaces remains largely unexplored. Compared to adversarial patches or stickers, which have fixed adversarial patterns, projection attacks allow for transient modifications to these patterns, enabling a more flexible attack. In this paper, we introduce an adversarial 3D projection attack specifically targeting object detection in autonomous driving scenarios. We frame the attack formulation as an optimization problem, utilizing a combination of color mapping and geometric transformation models. Our results demonstrate the effectiveness of the proposed attack in deceiving YOLOv3 and Mask R-CNN in physical settings. Evaluations conducted in an indoor environment show an attack success rate of up to 100% under low ambient light conditions, highlighting the potential damage of our attack in real-world driving scenarios.

📄 PDF Abstract BibTeX arXiv:2409.17403

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…
Batch Normalization 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
BNB Customer Service Number +1-833-534-1729 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifiers

2020-12-10 · Bingyao Huang, Haibin Ling

Light-based adversarial attacks use spatial augmented reality (SAR) techniques to fool image classifiers by altering the physical light condition with a controllable light source, e.g., a projector. Compared with physica…

Adversarial Attack

Fool the Hydra: Adversarial Attacks against Multi-view Object Detection Systems

2023-11-30 · Bilel Tarchoun, Quazi Mishkatul Alam, Nael Abu-Ghazaleh, Ihsen Alouani

Adversarial patches exemplify the tangible manifestation of the threat posed by adversarial attacks on Machine Learning (ML) models in real-world scenarios. Robustness against these attacks is of the utmost importance wh…

object-detectionObject DetectionOcclusion Handling

Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detection

2025-08-24 · Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen arxiv

Out-of-distribution (OOD) detection ensures safe and reliable model deployment. Contemporary OOD algorithms using geometry projection can detect OOD or adversarial samples from clean in-distribution (ID) samples. However…

Out-of-Distribution Detection

DPAttack: Diffused Patch Attacks against Universal Object Detection

2020-10-16 · Shudeng Wu, Tao Dai, Shu-Tao Xia

Recently, deep neural networks (DNNs) have been widely and successfully used in Object Detection, e.g. Faster RCNN, YOLO, CenterNet. However, recent studies have shown that DNNs are vulnerable to adversarial attacks. Adv…

Objectobject-detectionObject Detection

Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving

2021-01-17 · James Tu, Huichen Li, Xinchen Yan, Mengye Ren 외

Modern self-driving perception systems have been shown to improve upon processing complementary inputs such as LiDAR with images. In isolation, 2D images have been found to be extremely vulnerable to adversarial attacks.…

Adversarial RobustnessDenoisingSensor Fusion