paper-with-me

Papers

Targeted Nonlinear Adversarial Perturbations in Images and Videos

2018-08-27 · Roberto Rey-de-Castro, Herschel Rabitz

We introduce a method for learning adversarial perturbations targeted to individual images or videos. The learned perturbations are found to be sparse while at the same time containing a high level of feature detail. Thus, the extracted perturbations allow a form of object or action recognition and provide insights into what features the studied deep neural network models consider important when reaching their classification decisions. From an adversarial point of view, the sparse perturbations successfully confused the models into misclassifying, although the perturbed samples still belonged to the same original class by visual examination. This is discussed in terms of a prospective data augmentation scheme. The sparse yet high-quality perturbations may also be leveraged for image or video compression.

📄 PDF Abstract BibTeX arXiv:1809.00958

Code (1)

roberto1648/adversarial-perturbations-on-images-and-videos 공식 구현 pytorch

Tasks

Action RecognitionData AugmentationGeneral ClassificationTemporal Action LocalizationVideo Compression

Similar Papers 제목 키워드 기반

Sparse Adversarial Perturbations for Videos

2018-03-07 · Xingxing Wei, Jun Zhu, Hang Su

Although adversarial samples of deep neural networks (DNNs) have been intensively studied on static images, their extensions in videos are never explored. Compared with images, attacking a video needs to consider not onl…

Action RecognitionTemporal Action Localization

Enhancing the Self-Universality for Transferable Targeted Attacks

2022-09-08 · CVPR 2023 1 · Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

In this paper, we propose a novel transfer-based targeted attack method that optimizes the adversarial perturbations without any extra training efforts for auxiliary networks on training data. Our new attack method is pr…

A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Tracking

2021-05-06 · Zhenbang Li, Yaya Shi, Jin Gao, Shaoru Wang 외

Siamese trackers are shown to be vulnerable to adversarial attacks recently. However, the existing attack methods craft the perturbations for each video independently, which comes at a non-negligible computational cost. …

Visual Tracking

Understanding Adversarial Examples from the Mutual Influence of Images and Perturbations

2020-07-13 · CVPR 2020 6 · Chaoning Zhang, Philipp Benz, Tooba Imtiaz, In-So Kweon

A wide variety of works have explored the reason for the existence of adversarial examples, but there is no consensus on the explanation. We propose to treat the DNN logits as a vector for feature representation, and exp…

LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations

2023-10-31 · Kunyu Wang, Juluan Shi, Wenxuan Wang

Deep neural networks are susceptible to adversarial attacks, which pose a significant threat to their security and reliability in real-world applications. The most notable adversarial attacks are transfer-based attacks, …

Adversarial Attack