Adversarial Learning of Privacy-Preserving and Task-Oriented Representations
نویسندگان
چکیده
منابع مشابه
Learning Privacy Preserving Encodings through Adversarial Training
We present a framework to learn privacypreserving encodings of images (or other highdimensional data) to inhibit inference of a chosen private attribute. Rather than encoding a fixed dataset or inhibiting a fixed estimator, we aim to to learn an encoding function such that even after this function is fixed, an estimator with knowledge of the encoding is unable to learn to accurately predict the...
متن کاملPrivacy-Preserving Adversarial Networks
We propose a data-driven framework for optimizing privacy-preserving data release mechanisms toward the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing sensitive information. Our approach employs adversarially-trained neural networks to implement randomized mechanisms and to perform a variational approximation of mutual information privacy....
متن کاملPrivacy-Preserving Classifier Learning
We present an efficient protocol for the privacy-preserving, distributed learning of decision-tree classifiers. Our protocol allows a user to construct a classifier on a database held by a remote server without learning any additional information about the records held in the database. The server does not learn anything about the constructed classifier, not even the user’s choice of feature and...
متن کاملcompactifications and representations of transformation semigroups
this thesis deals essentially (but not from all aspects) with the extension of the notion of semigroup compactification and the construction of a general theory of semitopological nonaffine (affine) transformation semigroup compactifications. it determines those compactification which are universal with respect to some algebric or topological properties. as an application of the theory, it is i...
15 صفحه اولPerformance-Oriented Privacy-Preserving Data Integration
Current solutions to integrating private data with public data have provided useful privacy metrics, such as relative information gain, that can be used to evaluate alternative approaches. Unfortunately, they have not addressed critical performance issues, especially when the public database is very large. The use of hashes and noise yields better performance than existing techniques, while sti...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2020
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v34i07.6930