SA: Sliding Attack For Synthetic Speech Detection With Resistance To Clipping And Self-splicing

Abstract

Deep neural networks are vulnerable to adversarial examples that mislead models with imperceptible perturbations. In audio, although adversarial examples have achieved incredible attack success rates on white-box settings and black-box settings, most existing adversarial attacks are constrained by the input length. A More practical scenario is that the adversarial examples must be clipped or self-spliced and input into the black-box model. Therefore, it is necessary to explore how to improve transferability in different input length settings. In this paper, we take the synthetic speech detection task as an example and consider two representative SOTA models. We observe that the gradients of fragments with the same sample value are similar in different models via analyzing the gradients obtained by feeding samples into the model after cropping or self-splicing. Inspired by the above observation, we propose a new adversarial attack method termed sliding attack. Specifically, we make each

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjiacheng2022sa

Related papers

• Targeted Adversarial Examples For Black Box Audio Systems (2018)15.75
• Toward Improving Synthetic Audio Spoofing Detection Robustness Via Meta-learning And Disentangled Training With Adversarial Examples (2024)6.77
• Deep Residual Neural Networks For Audio Spoofing Detection (2019)0.00
• Adversarial Attack And Defense Strategies For Deep Speaker Recognition Systems (2020)13.39
• ALIF: Low-cost Adversarial Audio Attacks On Black-box Speech Platforms Using Linguistic Features (2024)7.16
• Towards Understanding And Mitigating Audio Adversarial Examples For Speaker Recognition (2022)11.67
• Multi-discriminator Sobolev Defense-gan Against Adversarial Attacks For End-to-end Speech Systems (2021)8.82
• Adversarial Attacks Against Automatic Speech Recognition Systems Via Psychoacoustic Hiding (2018)16.45