1,720,967 research outputs found
PRIVACY-AWARE COMMUNICATION OVER A WIRETAP CHANNEL WITH GENERATIVE NETWORKS
No full textWe study privacy-aware communication over a wiretap channel using end-to-end learning. Alice wants to transmit a source signal to Bob over a binary symmetric channel, while passive eavesdropper Eve tries to infer some sensitive attribute of Alice's source based on its overheard signal. Since we usually do not have access to true distributions, we propose a data-driven approach using variational autoencoder (VAE)-based joint source channel coding (JSCC). We show through simulations with the colored MNIST dataset that our approach provides high reconstruction quality at the receiver while confusing the eavesdropper about the latent sensitive attribute, which consists of the color and thickness of the digits. Finally, we consider a parallel-channel scenario, and show that our approach arranges the information transmission such that the channels with higher noise levels at the eavesdropper carry the sensitive information, while the non-sensitive information is transmitted over more vulnerable channels
Smart meter privacy
No full textThe newgeneration electricity supply network, called the smart grid (SG), provides consumers with an active management and control of the power. By utilizing digital communications and sensing technologies which make the grid smart, SGs yield more efficient electricity transmission, reduced peak demand, improved security and increased integration of renewable energy systems compared to the traditional grid. Smart meters (SMs) are one of the core enablers of SG systems; they measure and record the high resolution electricity consumption information of a household almost in a real time basis, and report it to the utility provider (UP) at regular time intervals. SM measurements can be used for time-of-use pricing, trading user-generated energy, and mitigating load variations. However, real-time SM readings can also reveal sensitive information about the consumer’s activities which the user may not want to share with the UP, resulting in serious privacy concerns. SM privacy enabling techniques proposed in the literature can be categorized as SM data manipulation and demand shaping. While the SMdata is modified before being reported to the UP in the former method, the latter requires direct manipulation of the real energy consumption by exploiting physical resources, such as a renewable energy source (RES) or a rechargeable battery (RB). In this chapter, a datamanipulation privacy-enabling technique and three different demand shaping privacy-enabling techniques are presented, considering SM with a RES and an RB, SM with only an RB andSMwith only a RES. Information theoretic measures are used to quantify SM privacy. Optimal energy management strategies and bounds which are obtained using control theory, specifically Markov decision processes (MDPs), and rate distortion theory are analyzed
Active privacy-utility trade-off against a hypothesis testing adversary
No full textWe consider a user releasing her data containing some personal information in return of a service. We model user’s personal information as two correlated random variables, one of them, called the secret variable, is to be kept private, while the other, called the useful variable, is to be disclosed for utility. We consider active sequential data release, where at each time step the user chooses from among a finite set of release mechanisms, each revealing some information about the user’s personal information, i.e., the true hypotheses, albeit with different statistics. The user manages data release in an online fashion such that maximum amount of information is revealed about the latent useful variable, while the confidence for the sensitive variable is kept below a predefined level. For the utility, we consider both the probability of correct detection of the useful variable and the mutual information (MI) between the useful variable and released data. We formulate both problems as a Markov decision process (MDP), and numerically solve them by advantage actor-critic (A2C) deep reinforcement learning (RL)
Distributed Coding of Shifts Using the DFT Phase
No full textIn this paper we consider the problem of image encoding with side information at the decoder, where the side information is an integer shifted version of the image at the encoder. The encoder is asked to send the shift of its own image with respect to the side information which is only available at the decoder. We propose a solution based on the encoding of the phase sign of the DFT coefficients, taken at exponentially spaced positions. We first introduce the method under ideal hypothesis, i.e. noiseless conditions without border effects, giving a theoretical foundation to the technique. Then, we consider the more realistic case of noisy images with border effects, showing the effectiveness of the proposed method
Privacy-aware time-series data sharing with deep reinforcement learning
Full text linkInternet of things (IoT) devices are becoming increasingly popular thanks to many new services and applications they offer. However, in addition to their many benefits, they raise privacy concerns since they share fine-grained time-series user data with untrusted third parties. In this work, we study the privacy-utility trade-off (PUT) in time-series data sharing. Existing approaches to PUT mainly focus on a single data point; however, temporal correlations in time-series data introduce new challenges. Methods that preserve the privacy for the current time may leak significant amount of information at the trace level as the adversary can exploit temporal correlations in a trace. We consider sharing the distorted version of a user’s true data sequence with an untrusted third party. We measure the privacy leakage by the mutual information between the user’s true data sequence and shared version. We consider both the instantaneous and average distortion between the two sequences, under a given distortion measure, as the utility loss metric. To tackle the history-dependent mutual information minimization, we reformulate the problem as a Markov decision process (MDP), and solve it using asynchronous actor-critic deep reinforcement learning (RL). We evaluate the performance of the proposed solution in location trace privacy on both synthetic and GeoLife GPS trajectory datasets. For the latter, we show the validity of our solution by testing the privacy of the released location trajectory against an adversary network
Privacy-Aware Location Sharing with Deep Reinforcement Learning
No full textLocation-based services (LBSs) have become widely popular. Despite their utility, these services raise concerns for privacy since they require sharing location information with untrusted third parties. In this work, we study privacy-utility trade-off in location sharing mechanisms. Existing approaches are mainly focused on privacy of sharing a single location or myopic location trace privacy; neither of them taking into account the temporal correlations between the past and current locations. Although these methods preserve the privacy for the current time, they may leak significant amount of information at the trace level as the adversary can exploit temporal correlations in a trace. We propose an information theoretically optimal privacy preserving location release mechanism that takes temporal correlations into account. We measure the privacy leakage by the mutual information between the user's true and released location traces. To tackle the history-dependent mutual information minimization, we reformulate the problem as a Markov decision process (MDP), and solve it using asynchronous actor-critic deep reinforcement learning (RL)
AI-Based Reconstruction for Fast MRI-A Systematic Review and Meta-Analysis
Full text linkCompressed sensing (CS) has been playing a key role in accelerating the magnetic resonance imaging (MRI) acquisition process. With the resurgence of artificial intelligence, deep neural networks and CS algorithms are being integrated to redefine the state of the art of fast MRI. The past several years have witnessed substantial growth in the complexity, diversity, and performance of deep-learning-based CS techniques that are dedicated to fast MRI. In this meta-analysis, we systematically review the deep-learning-based CS techniques for fast MRI, describe key model designs, highlight breakthroughs, and discuss promising directions. We have also introduced a comprehensive analysis framework and a classification system to assess the pivotal role of deep learning in CS-based acceleration for MRI
- …
