# Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features

arXiv: https://arxiv.org/abs/2406.19815 · HTML: https://mlsanity.com/paper/2406.19815/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 28 Jun 2024.

## Builds on (most cited first, 19 of 19)

- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/1904.01189/) (2019)
- [Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation](https://mlsanity.com/paper/1804.06055/) (2018)
- [Adversarial Attacks on Deep Neural Networks for Time Series Classification](https://mlsanity.com/paper/1903.07054/) (2019)
- [Speech Emotion Recognition using Self-Supervised Features](https://mlsanity.com/paper/2202.03896/) (2022)
- [Adversarial Attacks on Time Series](https://mlsanity.com/paper/1902.10755/) (2019)
- [Adversarial Attack on Skeleton-based Human Action Recognition](https://mlsanity.com/paper/1909.06500/) (2019)
- [Robust Tracking against Adversarial Attacks](https://mlsanity.com/paper/2007.09919/) (2020)
- [BASAR:Black-box Attack on Skeletal Action Recognition](https://mlsanity.com/paper/2103.05266/) (2021)
- [Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack](https://mlsanity.com/paper/2103.05347/) (2021)
- [Fusing ASR Outputs in Joint Training for Speech Emotion Recognition](https://mlsanity.com/paper/2110.15684/) (2021)
- [ProxEmo: Gait-based Emotion Learning and Multi-view Proxemic Fusion for Socially-Aware Robot Navigation](https://mlsanity.com/paper/2003.01062/) (2020)
- [Group Gated Fusion on Attention-based Bidirectional Alignment for Multimodal Emotion Recognition](https://mlsanity.com/paper/2201.06309/) (2022)
- [Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition](https://mlsanity.com/paper/2005.07151/) (2020)
- [EvoGAN: An Evolutionary Computation Assisted GAN](https://mlsanity.com/paper/2110.11583/) (2021)
- [TNTC: two-stream network with transformer-based complementarity for gait-based emotion recognition](https://mlsanity.com/paper/2110.13708/) (2021)
- [Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-trained Representations](https://mlsanity.com/paper/2302.13277/) (2023)
- [LMR-CBT: Learning Modality-fused Representations with CB-Transformer for Multimodal Emotion Recognition from Unaligned Multimodal Sequences](https://mlsanity.com/paper/2112.01697/) (2021)

## Abstract (arXiv)

Adversarial attack on skeletal motion is a hot topic. However, existing researches only consider part of dynamic features when measuring distance between skeleton graph sequences, which results in poor imperceptibility. To this end, we propose a novel adversarial attack method to attack action recognizers for skeletal motions. Firstly, our method systematically proposes a dynamic distance function to measure the difference between skeletal motions. Meanwhile, we innovatively introduce emotional features for complementary information. In addition, we use Alternating Direction Method of Multipliers(ADMM) to solve the constrained optimization problem, which generates adversarial samples with better imperceptibility to deceive the classifiers. Experiments show that our method is effective on multiple action classifiers and datasets. When the perturbation magnitude measured by l norms is the same, the dynamic perturbations generated by our method are much lower than that of other methods. What's more, we are the first to prove the effectiveness of emotional features, and provide a new idea for measuring the distance between skeletal motions.