# Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack

arXiv: https://arxiv.org/abs/2011.14585 · HTML: https://mlsanity.com/paper/2011.14585/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 12 of 12)

- [Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos](https://mlsanity.com/paper/2301.00896/) (2023)
- [Defending Black-box Skeleton-based Human Activity Classifiers](https://mlsanity.com/paper/2203.04713/) (2022)
- [Adversarial Attacks on Video Object Segmentation with Hard Region Discovery](https://mlsanity.com/paper/2309.13857/) (2023)
- [Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models](https://mlsanity.com/paper/2311.10366/) (2023)
- [Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks](https://mlsanity.com/paper/2112.07921/) (2021)
- [Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack](https://mlsanity.com/paper/2211.11312/) (2022)
- [Multimodal Attack Detection for Action Recognition Models](https://mlsanity.com/paper/2404.10790/) (2024)
- [VideoPure: Diffusion-based Adversarial Purification for Video Recognition](https://mlsanity.com/paper/2501.14999/) (2025)
- [Similarity of Neural Architectures using Adversarial Attack Transferability](https://mlsanity.com/paper/2210.11407/) (2022)
- [Amicable Aid: Perturbing Images to Improve Classification Performance](https://mlsanity.com/paper/2112.04720/) (2021)
- [Adversarially Robust Video Perception by Seeing Motion](https://mlsanity.com/paper/2212.07815/) (2022)
- [Robustness Evaluation for Video Models with Reinforcement Learning](https://mlsanity.com/paper/2506.05431/) (2025)

## Abstract (arXiv)

The video-based action recognition task has been extensively studied in recent years. In this paper, we study the structural vulnerability of deep learning-based action recognition models against the adversarial attack using the one frame attack that adds an inconspicuous perturbation to only a single frame of a given video clip. Our analysis shows that the models are highly vulnerable against the one frame attack due to their structural properties. Experiments demonstrate high fooling rates and inconspicuous characteristics of the attack. Furthermore, we show that strong universal one frame perturbations can be obtained under various scenarios. Our work raises the serious issue of adversarial vulnerability of the state-of-the-art action recognition models in various perspectives.