Zero-query Adversarial Attack On Black-box Automatic Speech Recognition Systems

Abstract

In recent years, extensive research has been conducted on the vulnerability of ASR systems, revealing that black-box adversarial example attacks pose significant threats to real-world ASR systems. However, most existing black-box attacks rely on queries to the target ASRs, which is impractical when queries are not permitted. In this paper, we propose ZQ-Attack, a transfer-based adversarial attack on ASR systems in the zero-query black-box setting. Through a comprehensive review and categorization of modern ASR technologies, we first meticulously select surrogate ASRs of diverse types to generate adversarial examples. Following this, ZQ-Attack initializes the adversarial perturbation with a scaled target command audio, rendering it relatively imperceptible while maintaining effectiveness. Subsequently, to achieve high transferability of adversarial perturbations, we propose a sequential ensemble optimization algorithm, which iteratively optimizes the adversarial perturbation on each sur

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keyfang2024zero

Related papers

• QFA2SR: Query-free Adversarial Transfer Attacks To Speaker Recognition Systems (2023)0.00
• Targeted Adversarial Examples For Black Box Audio Systems (2018)15.75
• ALIF: Low-cost Adversarial Audio Attacks On Black-box Speech Platforms Using Linguistic Features (2024)7.16
• Adversarial Attacks Against Automatic Speech Recognition Systems Via Psychoacoustic Hiding (2018)16.45
• Inaudible Adversarial Perturbations For Targeted Attack In Speaker Recognition (2020)12.33
• Universal Adversarial Perturbations For Speech Recognition Systems (2019)14.11
• Adjust-free Adversarial Example Generation In Speech Recognition Using Evolutionary Multi-objective Optimization Under Black-box Condition (2020)6.77
• Towards Understanding And Mitigating Audio Adversarial Examples For Speaker Recognition (2022)11.67