Towards the Transferable Audio Adversarial Attack via Ensemble Methods
Not on the map. Why?
Abstract (arXiv)
In recent years, deep learning (DL) models have achieved significant progress in many domains, such as autonomous driving, facial recognition, and speech recognition. However, the vulnerability of deep learning models to adversarial attacks has raised serious concerns in the community because of their insufficient robustness and generalization. Also, transferable attacks have become a prominent method for black-box attacks. In this work, we explore the potential factors that impact adversarial examples (AEs) transferability in DL-based speech recognition. We also discuss the vulnerability of different DL systems and the irregular nature of decision boundaries. Our results show a remarkable difference in the transferability of AEs between speech and images, with the data relevance being low in images but opposite in speech recognition. Motivated by dropout-based ensemble approaches, we propose random gradient ensembles and dynamic gradient-weighted ensembles, and we evaluate the impact of ensembles on the transferability of AEs. The results show that the AEs created by both approaches are valid for transfer to the black box API.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 37 of its 47 references that are in the map. First posted on arXiv 18 Apr 2023.
Builds on
37 of 47 references.
References · 37
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2017SmoothGrad: removing noise by adding noisecited by 1,097
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
- 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
- 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
- 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
25 more
- 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 165
- 2017The Shattered Gradients Problem: If resnets are the answer, then what is the question?cited by 156
- 2017The Space of Transferable Adversarial Examplescited by 156
- 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
- 2022Frequency Domain Model Augmentation for Adversarial Attackcited by 128
- 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 123
- 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 123
- 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
- 2018Learning Transferable Adversarial Examples via Ghost Networkscited by 69
- 2018CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognitioncited by 63
- 2018Understanding and Enhancing the Transferability of Adversarial Examplescited by 41
- 2018Targeted Adversarial Examples for Black Box Audio Systemscited by 41
- 2019Universal Adversarial Perturbations for Speech Recognition Systemscited by 41
- 2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 36
- 2019SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systemscited by 33
- 2022Robust Training of Neural Networks Using Scale Invariant Architecturescited by 29
- 2021Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Informationcited by 25
- 2020Adversarial Examples on Object Recognition: A Comprehensive Surveycited by 23
- 2016The Microsoft 2016 Conversational Speech Recognition Systemcited by 9
- 2019A New Ensemble Adversarial Attack Powered by Long-term Gradient Memoriescited by 9
- 2022Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attackscited by 7
- 2022Noise-robust voice conversion with domain adversarial trainingcited by 5
- 2021SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systemscited by 4
- 2022Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defensescited by 2
- 2022Disappeared Command: Spoofing Attack On Automatic Speech Recognition Systems with Sound Maskingcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.