Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks

• URL: http://arxiv.org/abs/2606.20893v1
• Date: Thu, 18 Jun 2026 19:40:46 GMT
• Title: Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks
• Abstract summary: We propose a generative attack framework operating in the latent space of a neural audio.<n>A conditional generator synthesizes class-specific perturbations in a single forward pass and decodes them into adversarial waveforms.<n>Our method targeted attack success rates up to 99% with sub-7 ms inference, outperforming generative baselines while reducing latency by 24x.
• Score: 2.3067587087700767
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning-based audio classification systems, including automatic speaker verification, are vulnerable to adversarial attacks. Realistic real-time threat assessment remains difficult because optimization-based methods, such as projected gradient descent (PGD) and Carlini-Wagner, require costly iterative updates in the high-dimensional waveform domain. Generative attacks allow single-shot synthesis but often introduce perceptible artifacts or depend on computationally intensive architectures, while diffusion and autoregressive approaches incur high inference latency. To address this gap, we propose a generative attack framework operating in the continuous latent space of a neural audio codec. A conditional generator synthesizes class-specific perturbations in a single forward pass and decodes them into adversarial waveforms. Our method achieves targeted attack success rates up to 99% with sub-7 ms inference, outperforming generative baselines while reducing latency by 24x.

Related papers

• GENADA: efficient generative time series adversarial attack framework [0.7493157444527366]
  We propose a GENerative ADrial Attack (GENADA) that learns a generative model to produce deceptive perturbations directly in a single forward pass.<n>The validation considers attacks on several neural models and datasets in the time-series domain.
  arXiv  Detail & Related papers  (2026-08-12T19:08:04Z)
• Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition [9.839293944956006]
  Existing adversarial attacks directly add adversarial noise to the speech audio.<n>Clean-Referenced Feature-Vocoder Attack moves the adversarial search space from raw waveforms to self-supervised learning representations.<n>Experiments show that, when optimized only on raw Whisper-small as a public surrogate model, our attack transfers effectively to black-box ASR models.
  arXiv  Detail & Related papers  (2026-06-04T04:00:48Z)
• Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection [22.306688903148046]
  Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text.<n>We propose textitAudioHijack, a framework that generates context-agnostic and imperceptible adversarial audio to hijack LALMs.<n>Experiments on 13 state-of-the-art LALMs show consistent hijacking across 6 categories misbehavior.
  arXiv  Detail & Related papers  (2026-04-16T04:22:11Z)
• Latent-Mark: An Audio Watermark Robust to Neural Resynthesis [62.09761127079914]
  Latent-Mark is the first zero-bit audio watermarking framework designed to survive semantic compression.<n>Our key insight is that robustness to the encode-decode process requires embedding the watermark within the invariant latent space.<n>Our work inspires future research into universal watermarking frameworks capable of maintaining integrity across increasingly complex and diverse generative distortions.
  arXiv  Detail & Related papers  (2026-03-05T15:51:09Z)
• Scores Know Bobs Voice: Speaker Impersonation Attack [8.404098071525473]
  We propose an inversion-based generative attack framework that aligns the latent space of a synthesis model with the discriminative feature space of SRSs.<n>Experiments show that our method significantly improves query efficiency, achieving competitive attack success rates with on average 10x fewer queries than prior approaches.
  arXiv  Detail & Related papers  (2026-03-03T09:20:48Z)
• FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge [13.43804949744336]
  FlowMur is a stealthy and practical audio backdoor attack that can be launched with limited knowledge. Experiments conducted on two datasets demonstrate that FlowMur achieves high attack performance in both digital and physical settings.
  arXiv  Detail & Related papers  (2023-12-15T10:26:18Z)
• Histogram Layer Time Delay Neural Networks for Passive Sonar Classification [58.720142291102135]
  A novel method combines a time delay neural network and histogram layer to incorporate statistical contexts for improved feature learning and underwater acoustic target classification. The proposed method outperforms the baseline model, demonstrating the utility in incorporating statistical contexts for passive sonar target recognition.
  arXiv  Detail & Related papers  (2023-07-25T19:47:26Z)
• Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation [111.61781272232646]
  It is imperative to ensure the robustness of deep learning models in critical applications such as, healthcare. We present a 3D frequency domain adversarial attack for volumetric medical image segmentation models.
  arXiv  Detail & Related papers  (2023-07-14T10:50:43Z)
• Adversarial Attacks with Time-Scale Representations [3.3865605512957457]
  We propose a novel framework for real-time black-box universal attacks. Our hypothesis is that perturbations produced in the wavelet space disrupt early convolutional layers more effectively than perturbations performed in the time domain. Our results show that wavelet-based perturbations consistently outperform time-based attacks.
  arXiv  Detail & Related papers  (2021-07-26T20:58:57Z)
• WaveTransform: Crafting Adversarial Examples via Input Decomposition [69.01794414018603]
  We introduce WaveTransform', that creates adversarial noise corresponding to low-frequency and high-frequency subbands, separately (or in combination) Experiments show that the proposed attack is effective against the defense algorithm and is also transferable across CNNs.
  arXiv  Detail & Related papers  (2020-10-29T17:16:59Z)
• Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition [56.844587127848854]
  We demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks. We employ a generative adversarial network based architecture to semantically generate adversarial high-quality gait silhouettes or video frames. The experimental results show that if only one-fortieth of the frames are attacked, the accuracy of the target model drops dramatically.
  arXiv  Detail & Related papers  (2020-02-22T10:08:42Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.