Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models - Archive ouverte HAL
Communication Dans Un Congrès Année : 2025

Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models

Astrid H F Kitchen
  • Fonction : Auteur
  • PersonId : 1423706
Marie S Jensen
  • Fonction : Auteur
  • PersonId : 1423707
Martin Gonzalez
Christophe Biscio
  • Fonction : Auteur
  • PersonId : 1423708

Résumé

Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existing work has utilised diffusion models (DMs) to purify adversarial examples, achieving state-of-the-art results in keyword spotting tasks, their effectiveness for more complex tasks such as sentence-level ASR remains unexplored. Additionally, the impact of the number of forward diffusion steps on performance is not well understood. In this paper, we systematically investigate the use of DMs for defending against adversarial attacks on sentences and examine the effect of varying forward diffusion steps. Through comprehensive experiments on the Mozilla Common Voice dataset, we demonstrate that two forward diffusion steps can completely defend against adversarial attacks on sentences. Moreover, we introduce a novel, training-free approach for detecting adversarial attacks by leveraging a pre-trained DM. Our experimental results show that this method can detect adversarial attacks with high accuracy.
Fichier principal
Vignette du fichier
Detecting_and_Defending_Against_Adversarial_Attacks_on_Automatic_Speech_Recognition_via_Diffusion_Models.pdf (808.03 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04726719 , version 1 (08-10-2024)

Identifiants

  • HAL Id : hal-04726719 , version 1

Citer

Nikolai L Kühne, Astrid H F Kitchen, Marie S Jensen, Mikkel S L Brøndt, Martin Gonzalez, et al.. Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Apr 2025, Hyderabad, India. ⟨hal-04726719⟩

Collections

IRT-SYSTEMX
33 Consultations
2 Téléchargements

Partager

More