mlsanityData to 7 Oct 2026

Adversarial Interaction Attack: Fooling AI to Misinterpret Human Intentions

arXiv 2101.06704 ↗First posted 17 Jan 2021cs.AI cs.CR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Understanding the actions of both humans and artificial intelligence (AI) agents is important before modern AI systems can be fully integrated into our daily life. In this paper, we show that, despite their current huge success, deep learning based AI systems can be easily fooled by subtle adversarial noise to misinterpret the intention of an action in interaction scenarios. Based on a case study of skeleton-based human interactions, we propose a novel adversarial attack on interactions, and demonstrate how DNN-based interaction models can be tricked to predict the participants' reactions in unexpected ways. From a broader perspective, the scope of our proposed attack method is not confined to problems related to skeleton data but can also be extended to any type of problems involving sequential regressions. Our study highlights potential risks in the interaction loop with AI and humans, which need to be carefully addressed when deploying AI systems in safety-critical applications.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 17 Jan 2021.

Builds on

39 of 55 references.

References · 39

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  10. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  11. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  12. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
27 more
  1. 2017One pixel attack for fooling deep neural networkscited by 579
  2. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  3. 2017Adversarial Patchcited by 514
  4. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  5. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  6. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  7. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 165
  8. 2017The Space of Transferable Adversarial Examplescited by 156
  9. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
  10. 2019An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognitioncited by 151
  11. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  12. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  13. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  14. 2018Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examplescited by 93
  15. 2017Interpretable 3D Human Action Analysis with Temporal Convolutional Networkscited by 88
  16. 2020A Unified Approach to Interpreting and Boosting Adversarial Transferabilitycited by 71
  17. 2019Black-box Adversarial Attacks on Video Recognition Modelscited by 58
  18. 2017Skeleton-based Action Recognition with Convolutional Neural Networkscited by 54
  19. 2017RGB-D-based Human Motion Recognition with Deep Learning: A Surveycited by 37
  20. 2020Improving Query Efficiency of Black-box Adversarial Attackcited by 34
  21. 2019Adversarial Attack on Skeleton-based Human Action Recognitioncited by 32
  22. 2018Distributionally Adversarial Attackcited by 24
  23. 2016RGB-D-based Action Recognition Datasets: A Surveycited by 14
  24. 2018DeepGRU: Deep Gesture Recognition Utilitycited by 14
  25. 2019White-Box Target Attack for EEG-Based BCI Regression Problemscited by 13
  26. 2020Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognitioncited by 12
  27. 2019SMART: Skeletal Motion Action Recognition aTtackcited by 4

Built on by

Not cited yet.