We consider a database $\vec{X} = (X_1,\cdots,X_n)$ containing the data of $n$ users. The data aggregator wants to publicise the database, but wishes to sanitise the dataset to hide sensitive data $S_i$ correlated to $X_i$. This setting is considered in the Privacy Funnel, which uses mutual information as a leakage metric. The downsides to this approach are that mutual information does not give worst-case guarantees, and that finding optimal sanitisation protocols can be computationally prohibitive. We tackle these problems by using differential privacy metrics, and by considering local protocols which operate on one entry at a time. We show that under both the Local Differential Privacy and Local Information Privacy leakage metrics, one can efficiently obtain optimal protocols; however, Local Information Privacy is both more closely aligned to the privacy requirements of the Privacy Funnel scenario, and more efficiently computable. We also consider the scenario where each user has multiple attributes (i.e. $X_i = (X^1_i,\cdots,X^m_i)$), for which we define \emph{Side-channel Resistant Local Information Privacy}, and we give efficient methods to find protocols satisfying this criterion while still offering good utility. Exploratory experiments confirm the validity of these methods.
In the Open Data approach, governments and other public organisations want to share their datasets with the public, for accountability and to support participation. Data must be opened in such a way that individual privacy is safeguarded. The Privacy Funnel is a mathematical approach that produces a sanitised database that does not leak private data beyond a chosen threshold. The downsides to this approach are that it does not give worst-case privacy guarantees, and that finding optimal sanitisation protocols can be computationally prohibitive. We tackle these problems by using differential pr…
We show how to achieve differential privacy with no or reduced added noise, based on the empirical noise in the data itself. Unlike previous works on noiseless privacy, the empirical viewpoint avoids making any explicit assumptions about the random process generating the data.
The recent spades of cyber security attacks have compromised end users' data safety and privacy in Medical Cyber-Physical Systems (MCPS). Traditional standard encryption algorithms for data protection are designed based on a viewpoint of system architecture rather than a viewpoint of end users. As such encryption algorithms are transferring the protection on the data to the protection on the keys, data safety and privacy will be compromised once the key is exposed. In this paper, we propose a secure data storage and sharing method consisted by a selective encryption algorithm combined with fra…
AP-HP（巴黎公立医院集团）；Inserm（法国国家健康与医学研究院）；Université Paris-Saclay（巴黎萨克雷大学）；Centre Hospitalier Universitaire Grenoble Alpes（格勒诺布尔阿尔卑斯大学中心医院）；School of Clinical Medicine, University of Cambridge（剑桥大学临床医学院）；University College London（伦敦大学学院）
We consider the problem of privacy-preserving data release for a specific utility task under perfect obfuscation constraint. We establish the necessary and sufficient condition to extract features of the original data that carry as much information about a utility attribute as possible, while not revealing any information about the sensitive attribute. This problem formulation generalizes both the information bottleneck and privacy funnel problems. We adopt a local information geometry analysis that provides useful insight into information coupling and trajectory construction of spherical pert…
In this rejoinder, we aim to address two broad issues that cover most comments made in the discussion. First, we discuss some theoretical aspects of our work and comment on how this work might impact the theoretical foundation of privacy-preserving data analysis. Taking a practical viewpoint, we next discuss how f-differential privacy (f-DP) and Gaussian differential privacy (GDP) can make a difference in a range of applications.
McGill University（麦吉尔大学）；CentraleSupélec（中央理工-高等电力学院）；CNRS（法国国家科学研究中心）；Université Paris Sud（巴黎第十一大学）；Montreal Institute for Learning Algorithms (Mila)（蒙特利尔学习算法研究所）；Université de Montréal（蒙特利尔大学）
Smart Meters (SMs) are able to share the power consumption of users with utility providers almost in real-time. These fine-grained signals carry sensitive information about users, which has raised serious concerns from the privacy viewpoint. In this paper, we focus on real-time privacy threats, i.e., potential attackers that try to infer sensitive information from SMs data in an online fashion. We adopt an information-theoretic privacy measure and show that it effectively limits the performance of any attacker. Then, we propose a general formulation to design a privatization mechanism that can…
Sichuan University（四川大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Differential privacy (DP) is an essential technique for privacy-preserving. It was found that a large model trained for privacy preserving performs worse than a smaller model (e.g. ResNet50 performs worse than ResNet18). To better understand this phenomenon, we study high dimensional DP learning from the viewpoint of generalization. Theoretically, we show that for the simple Gaussian model with even small DP noise, if the dimension is large enough, then the classification error can be as bad as the random guessing. Then we propose a feature selection method to reduce the size of the model, bas…
University of Geneva（日内瓦大学）；Harvard University（哈佛大学）；Imperial College London（帝国理工学院）
Bottleneck problems are an important class of optimization problems that have recently gained increasing attention in the domain of machine learning and information theory. They are widely used in generative models, fair machine learning algorithms, design of privacy-assuring mechanisms, and appear as information-theoretic performance bounds in various multi-user communication problems. In this work, we propose a general family of optimization problems, termed as complexity-leakage-utility bottleneck (CLUB) model, which (i) provides a unified theoretical framework that generalizes most of the …
Norwegian University of Science and Technology（挪威科技大学）；University of Oslo（奥斯陆大学）
With the development of IoT technologies in the past few years, a wide range of smart devices are deployed in a variety of environments aiming to improve the quality of human life in a cost efficient way. Due to the increasingly serious aging problem around the world, smart homes for elder healthcare have become an important IoT-based application, which not only enables elders' health to be properly monitored and taken care of, but also allows them to live more comfortably and independently in their houses. However, elders' privacy might be disclosed from smart homes due to non-fully protected…
The Chinese University of Hong Kong（香港中文大学）；University of Electronic Science and Technology of China（电子科技大学）；Peng Cheng Lab（鹏城实验室）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
Trustworthy artificial intelligence (AI) technology has revolutionized daily life and greatly benefited human society. Among various AI technologies, Federated Learning (FL) stands out as a promising solution for diverse real-world scenarios, ranging from risk evaluation systems in finance to cutting-edge technologies like drug discovery in life sciences. However, challenges around data isolation and privacy threaten the trustworthiness of FL systems. Adversarial attacks against data privacy, learning algorithm stability, and system confidentiality are particularly concerning in the context of…
Nanjing University of Science and Technology（南京理工大学）；Data61, CSIRO（联邦科学与工业研究组织Data61）；Tsinghua University（清华大学）；Princeton University（普林斯顿大学）
Federated learning (FL), as a type of collaborative machine learning framework, is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. Nevertheless, from a viewpoint of information theory, it is still possible for a curious server to infer private information from the shared models uploaded by MTs. To address this problem, we first make use of the concept of local differential privacy (LDP), and propose a user-level differential privacy (UDP) algorithm by adding artificial noise to the shared models before uploading them to servers. Accord…
Privacy preserving RFID (Radio Frequency Identification) authentication has been an active research area in recent years. Both forward security and backward security are required to maintain the privacy of a tag, i.e., exposure of a tag's secret key should not reveal the past or future secret keys of the tag. We envisage the need for a formal model for backward security for RFID protocol designs in shared key settings, since the RFID tags are too resource-constrained to support public key settings. However, there has not been much research on backward security for shared key environment since …
Data is the new oil; this refrain is repeated extensively in the age of internet tracking, machine learning, and data analytics. As data collection becomes more personal and pervasive, however, public pressure is mounting for privacy protection. In this atmosphere, developers have created applications to add noise to user attributes visible to tracking algorithms. This creates a strategic interaction between trackers and users when incentives to maintain privacy and improve accuracy are misaligned. In this paper, we conceptualize this conflict through an N+1-player, augmented Stackelberg game.…
Radio Frequency Identification (RFID) is appearing as a favorite technology for automated identification, which can be widely applied to many applications such as e-passport, supply chain management and ticketing. However, researchers have found many security and privacy problems along RFID technology. In recent years, many researchers are interested in RFID authentication protocols and their security flaws. In this paper, we analyze two of the newest RFID authentication protocols which proposed by Fu et al. and Li et al. from several security viewpoints. We present different attacks such as d…
As a promising candidate to complement traditional biometric modalities, brain biometrics using electroencephalography (EEG) data has received a widespread attention in recent years. However, compared with existing biometrics such as fingerprints and face recognition, research on EEG biometrics is still in its infant stage. Most of the studies focus on either designing signal elicitation protocols from the perspective of neuroscience or developing feature extraction and classification algorithms from the viewpoint of machine learning. These studies have laid the ground for the feasibility of u…
Every time the customer (individual or company) has to release personal information to its service provider (e.g., an online store or a cloud computing provider), it faces a trade-off between the benefits gained (enhanced or cheaper services) and the risks it incurs (identity theft and fraudulent uses). The amount of personal information released is the major decision variable in that trade-off problem, and has a proxy in the maximum loss the customer may incur. We find the conditions for a unique optimal solution to exist for that problem as that maximizing the customer's surplus. We also sho…
Data is the new oil; this refrain is repeated extensively in the age of internet tracking, machine learning, and data analytics. Social network analysis, cookie-based advertising, and government surveillance are all evidence of the use of data for commercial and national interests. Public pressure, however, is mounting for the protection of privacy. Frameworks such as differential privacy offer machine learning algorithms methods to guarantee limits to information disclosure, but they are seldom implemented. Recently, however, developers have made significant efforts to undermine tracking thro…
