SLMIA-SR: Speaker-level Membership Inference Attacks Against Speaker Recognition Systems

Abstract

Membership inference attacks allow adversaries to determine whether a particular example was contained in the model's training dataset. While previous works have confirmed the feasibility of such attacks in various applications, none has focused on speaker recognition (SR), a promising voice-based biometric recognition technique. In this work, we propose SLMIA-SR, the first membership inference attack tailored to SR. In contrast to conventional example-level attack, our attack features speaker-level membership inference, i.e., determining if any voices of a given speaker, either the same as or different from the given inference voices, have been involved in the training of a model. It is particularly useful and practical since the training and inference voices are usually distinct, and it is also meaningful considering the open-set nature of SR, namely, the recognition speakers were often not present in the training data. We utilize intra-similarity and inter-dissimilarity, two trainin

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keychen2023slmia

Related papers

• Who Is Real Bob? Adversarial Attacks On Speaker Recognition Systems (2019)16.28
• QFA2SR: Query-free Adversarial Transfer Attacks To Speaker Recognition Systems (2023)0.00
• Improving Membership Inference In ASR Model Auditing With Perturbed Loss Features (2024)0.00
• Diffattack: Diffusion-based Timbre-reserved Adversarial Attack In Speaker Identification (2025)0.00
• Towards Understanding And Mitigating Audio Adversarial Examples For Speaker Recognition (2022)11.67
• 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
• Inaudible Adversarial Perturbations For Targeted Attack In Speaker Recognition (2020)12.33