paper-with-me

Papers

Transferable Adversarial Attacks for Image and Video Object Detection

2018-11-30 · Xingxing Wei, Siyuan Liang, Ning Chen, Xiaochun Cao

Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, which denotes that the generated adversarial examples have low success rate to attack other kinds of detection methods, and high computation cost, which means that they need more time to generate an adversarial image, and therefore are difficult to deal with the video data. To address these issues, we utilize a generative mechanism to obtain the adversarial image and video. In this way, the processing time is reduced. To enhance the transferability, we destroy the feature maps extracted from the feature network, which usually constitutes the basis of object detectors. The proposed method is based on the Generative Adversarial Network (GAN) framework, where we combine the high-level class loss and low-level feature loss to jointly train the adversarial example generator. A series of experiments conducted on PASCAL VOC and ImageNet VID datasets show that our method can efficiently generate image and video adversarial examples, and more importantly, these adversarial examples have better transferability, and thus, are able to simultaneously attack two kinds of representative object detection models: proposal based models like Faster-RCNN, and regression based models like SSD.

📄 PDF Abstract BibTeX arXiv:1811.12641

Code (3)

LiangSiyuan21/Adversarial-Attacks-for-Image-and-Video-Object-Detection/tree/master/img_attack_with_attention pytorch
anonymous20210106/attack_detector pytorch
cheonlian/DeepfakeBlock tf

Tasks

Generative Adversarial NetworkObjectobject-detectionObject DetectionVideo Object Detection

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Non Maximum Suppression Non Maximum Suppression is a computer vision method that selects a single entity out of many overlapping entities (for example bounding boxes in object detection). The…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
SSD SSD is a single-stage object detection method that discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per…

Similar Papers 제목 키워드 기반

Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations

2022-07-18 · Hashmat Shadab Malik, Shahina K Kunhimon, Muzammal Naseer, Salman Khan 외

Transferable adversarial attacks optimize adversaries from a pretrained surrogate model and known label space to fool the unknown black-box models. Therefore, these attacks are restricted by the availability of an effect…

object-detectionObject DetectionVideo SegmentationVideo Semantic Segmentation

Cross-Modal Transferable Adversarial Attacks from Images to Videos

2021-12-10 · CVPR 2022 1 · Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

Recent studies have shown that adversarial examples hand-crafted on one white-box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which…

Video Recognition

Feature Importance-aware Transferable Adversarial Attacks

2021-07-29 · ICCV 2021 10 · Zhibo Wang, Hengchang Guo, Zhifei Zhang, Wenxin Liu 외

Transferability of adversarial examples is of central importance for attacking an unknown model, which facilitates adversarial attacks in more practical scenarios, e.g., black-box attacks. Existing transferable attacks t…

Feature Importance

Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers

2020-12-30 · Krishna Kanth Nakka, Mathieu Salzmann

In recent years, the trackers based on Siamese networks have emerged as highly effective and efficient for visual object tracking (VOT). While these methods were shown to be vulnerable to adversarial attacks, as most dee…

Object TrackingVisual Object Tracking

TRAIL: Transferable Robust Adversarial Images via Latent diffusion

2025-05-22 · Yuhao Xue, Zhifei Zhang, Xinyang Jiang, Yifei Shen 외

Adversarial attacks exploiting unrestricted natural perturbations present severe security risks to deep learning systems, yet their transferability across models remains limited due to distribution mismatches between gen…

DenoisingTest-time Adaptation