paper-with-me

Papers

Sparse Adversarial Video Attacks with Spatial Transformations

2021-11-10 · Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino, Qiang Ni

In recent years, a significant amount of research efforts concentrated on adversarial attacks on images, while adversarial video attacks have seldom been explored. We propose an adversarial attack strategy on videos, called DeepSAVA. Our model includes both additive perturbation and spatial transformation by a unified optimisation framework, where the structural similarity index (SSIM) measure is adopted to measure the adversarial distance. We design an effective and novel optimisation scheme which alternatively utilizes Bayesian optimisation to identify the most influential frame in a video and Stochastic gradient descent (SGD) based optimisation to produce both additive and spatial-transformed perturbations. Doing so enables DeepSAVA to perform a very sparse attack on videos for maintaining human imperceptibility while still achieving state-of-the-art performance in terms of both attack success rate and adversarial transferability. Our intensive experiments on various types of deep neural networks and video datasets confirm the superiority of DeepSAVA.

📄 PDF Abstract BibTeX arXiv:2111.05468

Code (1)

trustai/deepsava 공식 구현 tf

Tasks

Adversarial AttackBayesian OptimisationSSIM

Similar Papers 제목 키워드 기반

Identifying and Resisting Adversarial Videos Using Temporal Consistency

2019-09-11 · Xiaojun Jia, Xingxing Wei, Xiaochun Cao

Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to…

Video Classification

Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition

2020-02-22 · Ziwen He, Wei Wang, Jing Dong, Tieniu Tan

Gait recognition is widely used in social security applications due to its advantages in long-distance human identification. Recently, sequence-based methods have achieved high accuracy by learning abundant temporal and …

Adversarial AttackGait RecognitionGenerative Adversarial Network

Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations

2021-10-05 · NeurIPS 2021 12 · Shasha Li, Abhishek Aich, Shitong Zhu, M. Salman Asif 외

When compared to the image classification models, black-box adversarial attacks against video classification models have been largely understudied. This could be possible because, with video, the temporal dimension poses…

Classificationimage-classificationImage ClassificationVideo Classification

A Unified Spatial Alignment Framework for Highly Transferable Transformation-Based Attacks on Spatially Structured Tasks

2026-03-26 · Jiaming Liang, Chi-Man Pun arxiv

Transformation-based adversarial attacks (TAAs) demonstrate strong transferability when deceiving classification models. However, existing TAAs often perform unsatisfactorily or even fail when applied to structured tasks…

Semantic SegmentationObject Detection

Provable Defenses against Spatially Transformed Adversarial Inputs: Impossibility and Possibility Results

2019-05-01 · ICLR 2019 5 · Xinyang Zhang, Yifan Huang, Chanh Nguyen, Shouling Ji 외

One intriguing property of neural networks is their inherent vulnerability to adversarial inputs, which are maliciously crafted samples to trigger target networks to misbehave. The state-of-the-art attacks generate adver…