Journal
IEEE TRANSACTIONS ON SIGNAL PROCESSING
Volume 70, Issue -, Pages 4031-4046Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSP.2022.3192171
Keywords
Privacy; Convergence; Optimization; Servers; Inference algorithms; Data privacy; Signal processing algorithms; ADMM; inference; privacy
Categories
Funding
- National Science Foundation [CCF-1717943, ECCS-1711468, CNS-1824553, CCF-1908258, DOI: 10.1109/ICASSP39728.2021.9413438]
Ask authors/readers for more resources
This paper proposes a general framework to balance inference accuracy and privacy protection in the inference as service scenario. By preprocessing data and using a privacy-preserving mapping, privacy can be protected while reducing inference accuracy. An optimization problem is formulated to find the privacy-preserving mapping, and an iterative algorithm is developed to solve the problem.
In this paper, we propose a general framework to provide a desirable trade-off between inference accuracy and privacy protection in the inference as service scenario (IAS). Instead of sending data directly to the server, the user will preprocess the data through a privacy-preserving mapping, which will increase privacy protection but reduce inference accuracy. To properly address the trade-off between privacy protection and inference accuracy, we formulate an optimization problem to find the privacy-preserving mapping. Even though the problem is non-convex in general, we characterize nice structures of the problem and develop an iterative algorithm to find the desired privacy-preserving mapping, with convergence analysis provided under certain assumptions. From numerical examples, we observe that the proposed method has better performance than gradient ascent method in the convergence speed, solution quality and algorithm stability.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available