[PDF][PDF] A review of speech-centric trustworthy machine learning: Privacy, safety, and fairness
Speech-centric machine learning systems have revolutionized a number of leading
industries ranging from transportation and healthcare to education and defense …
industries ranging from transportation and healthcare to education and defense …
HP-MIA: A novel membership inference attack scheme for high membership prediction precision
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 …
privacy threats in recent years, especially in machine learning models. Most canonical MIAs …
Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment
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 …
hindering the large-scale deployment on resource-restricted devices (eg., smartphones). To …
SLMIA-SR: Speaker-level membership inference attacks against speaker recognition systems
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 …
was contained in the model's training dataset. While previous works have confirmed the …
Generation or Replication: Auscultating Audio Latent Diffusion Models
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 …
sound clips on demand from a text description has the potential to revolutionize how we …
An ensemble teacher-student learning approach with poisson sub-sampling to differential privacy preserving speech recognition
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 …
a collection of teacher models to issue some differential privacy (DP) guarantee for training …
Low-Resource Self-Supervised Learning with SSL-Enhanced TTS
Self-supervised learning (SSL) techniques have achieved remarkable results in various
speech processing tasks. Nonetheless, a significant challenge remains in reducing the …
speech processing tasks. Nonetheless, a significant challenge remains in reducing the …
A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability
J Zhu, J Zha, D Li, L Wang - arXiv preprint arXiv:2404.02462, 2024 - arxiv.org
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 …
confronts significant privacy concerns, especially in vision. In this paper, we aim to perform …
Private Data Leakage in Federated Human Activity Recognition for Wearable Healthcare Devices
K Chen, D Zhang, B Mi - arXiv preprint arXiv:2405.10979, 2024 - arxiv.org
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 …
user's activity status based on behavior and providing reasonable exercise …
[PDF][PDF] 高效率語音生成: 運算效率, 資料效率及其在語音自監督學習中的應用
許博竣 - 2024 - tdr.lib.ntu.edu.tw
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 …
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 …