QFA2SR: Query-free Adversarial Transfer Attacks To Speaker Recognition Systems

Abstract

Current adversarial attacks against speaker recognition systems (SRSs) require either white-box access or heavy black-box queries to the target SRS, thus still falling behind practical attacks against proprietary commercial APIs and voice-controlled devices. To fill this gap, we propose QFA2SR, an effective and imperceptible query-free black-box attack, by leveraging the transferability of adversarial voices. To improve transferability, we present three novel methods, tailored loss functions, SRS ensemble, and time-freq corrosion. The first one tailors loss functions to different attack scenarios. The latter two augment surrogate SRSs in two different ways. SRS ensemble combines diverse surrogate SRSs with new strategies, amenable to the unique scoring characteristics of SRSs. Time-freq corrosion augments surrogate SRSs by incorporating well-designed time-/frequency-domain modification functions, which simulate and approximate the decision boundary of the target SRS and distortions int

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2023qfa2sr

Related papers

• Zero-query Adversarial Attack On Black-box Automatic Speech Recognition Systems (2024)8.60
• Towards Understanding And Mitigating Audio Adversarial Examples For Speaker Recognition (2022)11.67
• Who Is Real Bob? Adversarial Attacks On Speaker Recognition Systems (2019)16.28
• SLMIA-SR: Speaker-level Membership Inference Attacks Against Speaker Recognition Systems (2023)6.77
• Adversarial Attack And Defense Strategies For Deep Speaker Recognition Systems (2020)13.39
• Inaudible Adversarial Perturbations For Targeted Attack In Speaker Recognition (2020)12.33
• Diffattack: Diffusion-based Timbre-reserved Adversarial Attack In Speaker Identification (2025)0.00
• SA: Sliding Attack For Synthetic Speech Detection With Resistance To Clipping And Self-splicing (2022)0.00