Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey
Not on the map. Why?
Abstract (arXiv)
A Machine-Critical Application is a system that is fundamentally necessary to the success of specific and sensitive operations such as search and recovery, rescue, military, and emergency management actions. Recent advances in Machine Learning, Natural Language Processing, voice recognition, and speech processing technologies have naturally allowed the development and deployment of speech-based conversational interfaces to interact with various machine-critical applications. While these conversational interfaces have allowed users to give voice commands to carry out strategic and critical activities, their robustness to adversarial attacks remains uncertain and unclear. Indeed, Adversarial Artificial Intelligence (AI) which refers to a set of techniques that attempt to fool machine learning models with deceptive data, is a growing threat in the AI and machine learning research community, in particular for machine-critical applications. The most common reason of adversarial attacks is to cause a malfunction in a machine learning model. An adversarial attack might entail presenting a model with inaccurate or fabricated samples as it's training data, or introducing maliciously designed data to deceive an already trained model. While focusing on speech recognition for machine-critical applications, in this paper, we first review existing speech recognition techniques, then, we investigate the effectiveness of adversarial attacks and defenses against these systems, before outlining research challenges, defense recommendations, and future work. This paper is expected to serve researchers and practitioners as a reference to help them in understanding the challenges, position themselves and, ultimately, help them to improve existing models of speech recognition for mission-critical applications. Keywords: Mission-Critical Applications, Adversarial AI, Speech Recognition Systems.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 50 of its 94 references that are in the map. First posted on arXiv 22 Feb 2022.
Builds on
50 of 94 references.
References · 50
- 2017Attention Is All You Needcited by 60,361
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2016Adversarial Machine Learning at Scalecited by 936
- 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
- 2015Listen, Attend and Spellcited by 543
- 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 451
- 2015Attention-Based Models for Speech Recognitioncited by 401
38 more
- 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
- 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
- 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
- 2018Neural Approaches to Conversational AIcited by 165
- 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 151
- 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 124
- 2019Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modelingcited by 86
- 2017DolphinAtack: Inaudible Voice Commandscited by 69
- 2014End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Resultscited by 68
- 2020Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspectivecited by 59
- 2018Large-Scale Visual Speech Recognitioncited by 57
- 2015Deep Multimodal Semantic Embeddings for Speech and Imagescited by 56
- 2019Efficient Adversarial Training with Transferable Adversarial Examplescited by 56
- 2017Houdini: Fooling Deep Structured Prediction Modelscited by 50
- 2018Did you hear that? Adversarial Examples Against Automatic Speech Recognitioncited by 48
- 2019Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reductioncited by 47
- 2018Targeted Adversarial Examples for Black Box Audio Systemscited by 41
- 2017English Conversational Telephone Speech Recognition by Humans and Machinescited by 40
- 2018Fooling End-to-end Speaker Verification by Adversarial Examplescited by 39
- 2016Very Deep Convolutional Networks for End-to-End Speech Recognitioncited by 34
- 2017Crafting Adversarial Examples For Speech Paralinguistics Applicationscited by 30
- 2021Adversarial Attacks and Defenses for Speech Recognition Systemscited by 20
- 2017Speech recognition for medical conversationscited by 18
- 2019A Robust Approach for Securing Audio Classification Against Adversarial Attackscited by 12
- 2018Training Augmentation with Adversarial Examples for Robust Speech Recognitioncited by 11
- 2018Noise Flooding for Detecting Audio Adversarial Examples Against Automatic Speech Recognitioncited by 10
- 2019Adversarial Example Detection by Classification for Deep Speech Recognitioncited by 10
- 2021Study of Pre-processing Defenses against Adversarial Attacks on State-of-the-art Speaker Recognition Systemscited by 10
- 2018Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustnesscited by 9
- 2018Isolated and Ensemble Audio Preprocessing Methods for Detecting Adversarial Examples against Automatic Speech Recognitioncited by 8
- 2018Multimodal Grounding for Sequence-to-Sequence Speech Recognitioncited by 8
- 2019Detecting Adversarial Attacks On Audiovisual Speech Recognitioncited by 8
- 2020An Empirical Study of Derivative-Free-Optimization Algorithms for Targeted Black-Box Attacks in Deep Neural Networkscited by 8
- 2014Building DNN Acoustic Models for Large Vocabulary Speech Recognitioncited by 6
- 2020Multimodal Speech Recognition with Unstructured Audio Maskingcited by 6
- 2020Looking Enhances Listening: Recovering Missing Speech Using Imagescited by 5
- 2019Improving the Performance of the LSTM and HMM Model via Hybridizationcited by 3
- 2020Full-Sum Decoding for Hybrid HMM based Speech Recognition using LSTM Language Modelcited by 3
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 1.
3 papers.