# SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models

arXiv: https://arxiv.org/abs/2101.10586 · HTML: https://mlsanity.com/paper/2101.10586/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 11 references that are in the map.
- First posted on arXiv 26 Jan 2021.

## Builds on (most cited first, 7 of 7)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Adversarial Attack on Skeleton-based Human Action Recognition](https://mlsanity.com/paper/1909.06500/) (2019)
- [Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks](https://mlsanity.com/paper/2009.02608/) (2020)
- [UnMask: Adversarial Detection and Defense Through Robust Feature Alignment](https://mlsanity.com/paper/2002.09576/) (2020)
- [Massif: Interactive Interpretation of Adversarial Attacks on Deep Learning](https://mlsanity.com/paper/2001.07769/) (2020)
- [NeuralDivergence: Exploring and Understanding Neural Networks by Comparing Activation Distributions](https://mlsanity.com/paper/1906.00332/) (2019)

## Built on by (most cited first, 1 of 1)

- [MAiVAR-T: Multimodal Audio-image and Video Action Recognizer using Transformers](https://mlsanity.com/paper/2308.03741/) (2023)

## Abstract (arXiv)

Skeleton-based human action recognition technologies are increasingly used in video based applications, such as home robotics, healthcare on aging population, and surveillance. However, such models are vulnerable to adversarial attacks, raising serious concerns for their use in safety-critical applications. To develop an effective defense against attacks, it is essential to understand how such attacks mislead the pose detection models into making incorrect predictions. We present SkeletonVis, the first interactive system that visualizes how the attacks work on the models to enhance human understanding of attacks.