IEEE Transactions on Information Forensics and Security · 2021 · 15 citations · 23 references
ComputingComputer ScienceInformation TheoryMachine LearningPrivacy EngineeringData PrivacyData ProtectionDifferential PrivacyDimensionality ReductionPrivacy-preserving ProtocolsDifferentially Private Machine LearningPrivate Machine LearningPrivate Query Answering
Private individual information are increasingly exposed through high-dimensional and high-order data, with the wide deployment of learning techniques. These data are typically expressed in form of tensors, but there is no principled way to guarantee privacy for tensor-valued queries. Conventional differential privacy is typically applied to scalar values without a precise definition on the shape of the queried data. Realizing that the conventional mechanisms do not take the data structural information into account, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Tensor Variate Gaussian</i> (TVG), a new <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$(\epsilon,\delta) $ </tex-math></inline-formula> -differential privacy mechanism for tensor-valued queries. We further introduce two mechanisms based on TVG with an improved utility by imposing the unimodal differentially-private noise. With the utility space available, the proposed mechanisms can be instantiated with an optimized utility, and the optimization problem has a closed-form solution scalable to large-scale problems. Finally, we experimentally test our mechanisms on a variety of datasets and models, demonstrating that TVG is superior than other state-of-the-art mechanisms on tensor-valued queries.
23
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
UCI Machine Learning Repository
Arthur Asuncion · Medical Entomology and Zoology · 2007 · 24.4K citations
Tensor Decompositions and Applications
Tamara G. Kolda, Brett W. Bader · SIAM Review · 2009 · 10.5K citations
Deep Learning with Differential Privacy
Martı́n Abadi, Andy Chu, Ian Goodfellow et al. · 2016 · 5.9K citations · Full text
Reading digits in natural images with unsupervised feature learning
Yuval Netzer · 2024 · 4.6K citations · Full text