Targeted Adversarial Examples For Black Box Audio Systems

Abstract

The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into incorrectly predicting a specified target with high confidence. Current work on fooling ASR systems have focused on white-box attacks, in which the model architecture and parameters are known. In this paper, we adopt a black-box approach to adversarial generation, combining the approaches of both genetic algorithms and gradient estimation to solve the task. We achieve a 89.25% targeted attack similarity after 3000 generations while maintaining 94.6% audio file similarity.

Stats

• citations125
• S2 citations—
• github stars0
• HF likes0
• heat score15.75
• arxiv keytaori2018targeted

Related papers

• Inaudible Adversarial Perturbations For Targeted Attack In Speaker Recognition (2020)12.33
• Zero-query Adversarial Attack On Black-box Automatic Speech Recognition Systems (2024)8.60
• ALIF: Low-cost Adversarial Audio Attacks On Black-box Speech Platforms Using Linguistic Features (2024)7.16
• SA: Sliding Attack For Synthetic Speech Detection With Resistance To Clipping And Self-splicing (2022)0.00
• Adjust-free Adversarial Example Generation In Speech Recognition Using Evolutionary Multi-objective Optimization Under Black-box Condition (2020)6.77
• Adversarial Attacks Against Automatic Speech Recognition Systems Via Psychoacoustic Hiding (2018)16.45
• Adversarial Attack And Defense Strategies For Deep Speaker Recognition Systems (2020)13.39
• Pseudo-siamese Network Based Timbre-reserved Black-box Adversarial Attack In Speaker Identification (2023)0.00