# STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition

arXiv: https://arxiv.org/abs/2402.01227 · HTML: https://mlsanity.com/paper/2402.01227/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 75 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 30 of 37)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings](https://mlsanity.com/paper/2104.03502/) (2021)
- [Dawn of the transformer era in speech emotion recognition: closing the valence gap](https://mlsanity.com/paper/2203.07378/) (2022)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [SparseFool: a few pixels make a big difference](https://mlsanity.com/paper/1811.02248/) (2018)
- [Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems](https://mlsanity.com/paper/1911.01840/) (2019)
- [Speech Emotion Recognition using Self-Supervised Features](https://mlsanity.com/paper/2202.03896/) (2022)
- [Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition](https://mlsanity.com/paper/2110.06309/) (2021)
- [Universal Adversarial Perturbations for Speech Recognition Systems](https://mlsanity.com/paper/1905.03828/) (2019)
- [SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systems](https://mlsanity.com/paper/1901.07846/) (2019)
- [Enabling Fast and Universal Audio Adversarial Attack Using Generative Model](https://mlsanity.com/paper/2004.12261/) (2020)
- [Audio Super Resolution using Neural Networks](https://mlsanity.com/paper/1708.00853/) (2017)
- [Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems](https://mlsanity.com/paper/2008.07685/) (2020)
- [Fusing ASR Outputs in Joint Training for Speech Emotion Recognition](https://mlsanity.com/paper/2110.15684/) (2021)
- [Attack on practical speaker verification system using universal adversarial perturbations](https://mlsanity.com/paper/2105.09022/) (2021)
- [Attention-Augmented End-to-End Multi-Task Learning for Emotion Prediction from Speech](https://mlsanity.com/paper/1903.12424/) (2019)
- [AERO: Audio Super Resolution in the Spectral Domain](https://mlsanity.com/paper/2211.12232/) (2022)
- [Speech Emotion Recognition using Semantic Information](https://mlsanity.com/paper/2103.02993/) (2021)
- [Improved Gradient based Adversarial Attacks for Quantized Networks](https://mlsanity.com/paper/2003.13511/) (2020)

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

- [Breaking Resource Barriers in Speech Emotion Recognition via Data Distillation](https://mlsanity.com/paper/2406.15119/) (2024)

## Abstract (arXiv)

Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction. The robustness of SER models is crucial, particularly in privacy-sensitive and reliability-demanding domains like private healthcare. Recently, the vulnerability of deep neural networks in the audio domain to adversarial attacks has become a popular area of research. However, prior works on adversarial attacks in the audio domain primarily rely on iterative gradient-based techniques, which are time-consuming and prone to overfitting the specific threat model. Furthermore, the exploration of sparse perturbations, which have the potential for better stealthiness, remains limited in the audio domain. To address these challenges, we propose a generator-based attack method to generate sparse and transferable adversarial examples to deceive SER models in an end-to-end and efficient manner. We evaluate our method on two widely-used SER datasets, Database of Elicited Mood in Speech (DEMoS) and Interactive Emotional dyadic MOtion CAPture (IEMOCAP), and demonstrate its ability to generate successful sparse adversarial examples in an efficient manner. Moreover, our generated adversarial examples exhibit model-agnostic transferability, enabling effective adversarial attacks on advanced victim models.