mlsanityData to 7 Oct 2026

Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack

arXiv 2103.05347 ↗First posted 9 Mar 2021cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Action recognition has been heavily employed in many applications such as autonomous vehicles, surveillance, etc, where its robustness is a primary concern. In this paper, we examine the robustness of state-of-the-art action recognizers against adversarial attack, which has been rarely investigated so far. To this end, we propose a new method to attack action recognizers that rely on 3D skeletal motion. Our method involves an innovative perceptual loss that ensures the imperceptibility of the attack. Empirical studies demonstrate that our method is effective in both white-box and black-box scenarios. Its generalizability is evidenced on a variety of action recognizers and datasets. Its versatility is shown in different attacking strategies. Its deceitfulness is proven in extensive perceptual studies. Our method shows that adversarial attack on 3D skeletal motions, one type of time-series data, is significantly different from traditional adversarial attack problems. Its success raises serious concern on the robustness of action recognizers and provides insights on potential improvements.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 34 of its 55 references that are in the map. First posted on arXiv 9 Mar 2021.

Builds on

34 of 55 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2017The Kinetics Human Action Video Datasetcited by 1,894
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  8. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  9. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  10. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  11. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  12. 2018Adversarial Attack on Graph Structured Datacited by 300
22 more
  1. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  2. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  3. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  4. 2018Spatially Transformed Adversarial Examplescited by 195
  5. 2017The Space of Transferable Adversarial Examplescited by 156
  6. 2018Generating 3D Adversarial Point Cloudscited by 144
  7. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 142
  8. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  9. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  10. 2016An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Datacited by 126
  11. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 125
  12. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  13. 2017Adversarial Attacks Beyond the Image Spacecited by 67
  14. 2018Sparse Adversarial Perturbations for Videoscited by 56
  15. 2019Adversarial Attacks on Deep Neural Networks for Time Series Classificationcited by 53
  16. 2019Adversarial Attacks on Time Seriescited by 40
  17. 2019Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modelingcited by 32
  18. 2019Adversarial Attack on Skeleton-based Human Action Recognitioncited by 32
  19. 2018The Adversarial Attack and Detection under the Fisher Information Metriccited by 18
  20. 2018Adversarial Attacks for Optical Flow-Based Action Recognition Classifierscited by 14
  21. 2020Dynamic Future Net: Diversified Human Motion Generationcited by 14
  22. 2020Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognitioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 3; 2023: 5; 2024: 8; 2025: 1; 2026: 1.

23 papers.

Sort:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2022Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loopcited by 30
  3. 2021Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognitioncited by 22
  4. 2023Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videoscited by 20
  5. 2021Adversarial Visual Robustness by Causal Interventioncited by 13
  6. 2021Adversarial Bone Length Attack on Action Recognitioncited by 10
  7. 2023Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradientcited by 10
  8. 2022Defending Black-box Skeleton-based Human Activity Classifierscited by 8
  9. 2022Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attackcited by 7
  10. 2024Towards Physical World Backdoor Attacks against Skeleton Action Recognitioncited by 7
  11. 2024TASAR: Transfer-based Attack on Skeletal Action Recognitioncited by 7
  12. 2024From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognitioncited by 6
11 more
  1. 2021Anonymization for Skeleton Action Recognitioncited by 5
  2. 2024Two-Person Interaction Augmentation with Skeleton Priorscited by 5
  3. 2023Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognitioncited by 2
  4. 2024Recovering Complete Actions for Cross-dataset Skeleton Action Recognitioncited by 2
  5. 2023Attack-Augmentation Mixing-Contrastive Skeletal Representation Learningcited by 1
  6. 2023Post-train Black-box Defense via Bayesian Boundary Correctioncited by 1
  7. 2024Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learningcited by 1
  8. 2024Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Featurescited by 0
  9. 2024Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Spacecited by 0
  10. 2025LatentStealth: Unnoticeable and Efficient Adversarial Attacks on Expressive Human Pose and Shape Estimationcited by 0
  11. 2026Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognitioncited by 0