Model Extraction Attack against Self-supervised Speech Models
Self-supervised learning (SSL) speech models generate meaningful representations of given clips and achieve incredible performance across various downstream tasks. Model extraction attack (MEA) often refers to an adversary stealing the functionality of the victim model with only query access. In this work, we study the MEA problem against SSL speech model with a small number of queries. We propose a two-stage framework to extract the model. In the first stage, SSL is conducted on the large-scale unlabeled corpus to pre-train a small speech model. Secondly, we actively sample a small portion of clips from the unlabeled corpus and query the target model with these clips to acquire their representations as labels for the small model's second-stage training. Experiment results show that our sampling methods can effectively extract the target model without knowing any information about its model architecture.
Code (0)
등록된 구현이 없습니다.
Tasks
modelModel extractionSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Membership Inference Attacks Against Self-supervised Speech Models
Recently, adapting the idea of self-supervised learning (SSL) on continuous speech has started gaining attention. SSL models pre-trained on a huge amount of unlabeled audio can generate general-purpose representations th…
Self-Supervised LearningMEA-Defender: A Robust Watermark against Model Extraction Attack
Recently, numerous highly-valuable Deep Neural Networks (DNNs) have been trained using deep learning algorithms. To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based water…
Model extractionSelf-Supervised LearningOn the Difficulty of Defending Self-Supervised Learning against Model Extraction
Self-Supervised Learning (SSL) is an increasingly popular ML paradigm that trains models to transform complex inputs into representations without relying on explicit labels. These representations encode similarity struct…
Model extractionSelf-Supervised LearningSpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech
This paper presents SpecWav-Attack, an adversarial model for detecting speakers in anonymized speech. It leverages Wav2Vec2 for feature extraction and incorporates spectrogram resizing and incremental training for improv…
Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning
High-performance anti-spoofing models for automatic speaker verification (ASV), have been widely used to protect ASV by identifying and filtering spoofing audio that is deliberately generated by text-to-speech, voice con…
Self-Supervised LearningSpeaker Verificationtext-to-speechText to Speech+1