Speech-centric machine learning systems have revolutionized a number of leading
industries ranging from transportation and healthcare to education and defense …

Abstract Membership Inference Attacks (MIAs) have been considered as one of the major
privacy threats in recent years, especially in machine learning models. Most canonical MIAs …

The size of deep learning models in artificial intelligence (AI) software is increasing rapidly,
hindering the large-scale deployment on resource-restricted devices (eg., smartphones). To …

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 …

The introduction of audio latent diffusion models possessing the ability to generate realistic
sound clips on demand from a text description has the potential to revolutionize how we …

We propose an ensemble learning framework with Poisson sub-sampling to effectively train
a collection of teacher models to issue some differential privacy (DP) guarantee for training …

Self-supervised learning (SSL) techniques have achieved remarkable results in various
speech processing tasks. Nonetheless, a significant challenge remains in reducing the …

Self-supervised learning shows promise in harnessing extensive unlabeled data, but it also
confronts significant privacy concerns, especially in vision. In this paper, we aim to perform …

Wearable wristband or watch can be utilized for health monitoring, such as determining the
user's activity status based on behavior and providing reasonable exercise …

摘要近年來, 隨著深度學習的進步, 許多語音生成模型展現了出色的表現.
儘管取得了亮眼的成果, 語音生成技術的發展也伴隨了對運算和資料資源的更大需求 …