Welcome to the resource topic for 2021/201
Title:
DAUnTLeSS: Data Augmentation and Uniform Transformation for Learning with Scalability and Security
Authors: Hanshen Xiao, Srinivas Devadas
Abstract:We revisit private optimization and learning from an information processing view. The main contribution of this paper is twofold. First, different from the classic cryptographic framework of operation-by-operation obfuscation, a novel private learning and inference framework via either random or data-dependent transformation on the sample domain is proposed. Second, we propose a novel security analysis framework, termed probably approximately correct (PAC) inference resistance, which bridges the information loss in data processing and prior knowledge. Using the entropy of private data, we develop an information theoretical security amplifier with a foundation of PAC security. We study the applications of such a framework from generalized linear regression models to modern learning techniques, such as deep learning. On the information theoretical privacy side, we compare three privacy interpretations: ambiguity, statistical indistinguishability (Differential Privacy) and PAC inference resistance, and precisely describe the information leakage of our framework. We show the advantages of this new random transform approach with respect to underlying privacy guarantees, computational efficiency and utility for fully-connected neural networks.
ePrint: https://eprint.iacr.org/2021/201
See all topics related to this paper.
Feel free to post resources that are related to this paper below.
Example resources include: implementations, explanation materials, talks, slides, links to previous discussions on other websites.
For more information, see the rules for Resource Topics .