Mobility patterns of vehicles and people provide powerful data sources for location-based services such as fleet optimization and traffic flow analysis. Location-based service providers must balance the value they extract from trajectory data with protecting the privacy of the individuals behind those trajectories. Reaching this goal requires measuring accurately the values of utility and privacy. Current measurement approaches assume adversaries with perfect knowledge, thus overestimate the privacy risk. To address this issue we introduce a model of an adversary with imperfect knowledge about the target. The model is based on equivalence areas, spatio-temporal regions with a semantic meaning, e.g. the target's home, whose size and accuracy determine the skill of the adversary. We then derive the standard privacy metrics of k-anonymity, l-diversity and t-closeness from the definition of equivalence areas. These metrics can be computed on any dataset, irrespective of whether and what kind of anonymization has been applied to it. This work is of high relevance to all service providers acting as processors of trajectory data who want to manage privacy risks and optimize the privacy vs. utility trade-off of their services.
Given the progressive nature of the world today, fairness is a very important social aspect in various areas, and it has long been studied with the advent of technology. To the best of our knowledge, methods of quantifying fairness errors and fairness in privacy threat models have been absent. To this end, in this short paper, we examine notions of fairness in privacy threat modelling due to different causes of privacy threats within a particular situation/context and that across contexts.
Causal questions often permeate in our day-to-day activities. With causal reasoning and counterfactual intuition, privacy threats can not only be alleviated but also prevented. In this paper, we discuss what is causal and counterfactual reasoning and how this can be applied in the field of privacy threat modelling (PTM). We believe that the future of PTM relies on how we can causally and counterfactually imagine cybersecurity threats and incidents.
Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data
Department of Neurosurgery, Qilu Hospital of Shandong University and Institute of Brain and Brain-Inspired Science（齐鲁医院山东大学神经外科和脑科学与脑启发科学研究院）；Department of Neurosurgery, The Affiliated Hospital of Qingdao University（青岛大学附属医院神经外科）；Department of Neurosurgery, Peking Union Medical College Hospital（北京地坛医院神经外科）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；College of Artificial Intelligence, Dalian Maritime University（大连海事大学人工智能学院）；University of Colorado Boulder（科罗拉多大学波尔德分校）；Zhengzhou University（郑州大学）；The University of Hong Kong（香港大学）；Georgia Institute of Technology（佐治亚理工学院）
A generalized distributed tool for mobility choice modelling is presented, where participants do not share personal raw data, while all computations are done locally. Participants use Blockchain based Smart Mobility Data-market (BSMD), where all transactions are secure and private. Nodes in blockchain can transact information with other participants as long as both parties agree to the transaction rules issued by the owner of the data. A case study is presented where a mode choice model is distributed and estimated over BSMD. As an example, the parameter estimation problem is solved on a distr…
Internet of Things (IoT) and cloud computing together give us the ability to sense, collect, process, and analyse data so we can use them to better understand behaviours, habits, preferences and life patterns of users and lead them to consume resources more efficiently. In such knowledge discovery activities, privacy becomes a significant challenge due to the extremely personal nature of the knowledge that can be derived from the data and the potential risks involved. Therefore, understanding the privacy expectations and preferences of stakeholders is an important task in the IoT domain. In th…
Helsinki Institute for Information Technology HIIT（赫尔辛基信息技术研究所）；University of Helsinki（赫尔辛基大学）；University of Manchester（曼彻斯特大学）；Aalto University（阿尔托大学）
Differential privacy allows quantifying privacy loss resulting from accessing sensitive personal data. Repeated accesses to underlying data incur increasing loss. Releasing data as privacy-preserving synthetic data would avoid this limitation, but would leave open the problem of designing what kind of synthetic data. We propose formulating the problem of private data release through probabilistic modelling. This approach transforms the problem of designing the synthetic data into choosing a model for the data, allowing also including prior knowledge, which improves the quality of the synthetic…
Nowadays different state and central government in India as well as abroad are taking initiative to deliver different kind of services electronically specially using Information and Communication Technology (ICT). Intruders or hackers can steal or modify the information communicated between Government and consumer through internet. To implement privacy and confidentiality of the information we must use suitable encryption technique. In this paper an Object Oriented Modelling of International Data Encryption Algorithm (IDEA) using GA based efficient key generation technique has been proposed to…
University of California, Santa Barbara（加州大学圣巴巴拉分校）
Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, either manually or automatically. In this paper, we propose Confidentially Redacted Training (CRT), a method to train language generation models while protecting the confidential segments. We borrow ideas from differential privacy (which solves a related but distinct problem) and show that our method is able to provably prevent unintended memorization by randomizing parts of the…
Recent work has shown that cell phone mobility data has the unique potential to create accurate models for human mobility and consequently the spread of infected diseases. While prior studies have exclusively relied on a mobile network operator's subscribers' aggregated data in modelling disease dynamics, it may be preferable to contemplate aggregated mobility data of infected individuals only. Clearly, naively linking mobile phone data with health records would violate privacy by either allowing to track mobility patterns of infected individuals, leak information on who is infected, or both. …
Multi-Continental Healthcare Modelling Using Blockchain-Enabled Federated Learning
School of Computing, Newcastle University（新castle大学计算机学院）；Department of Computing, Imperial College London（伦敦帝国理工学院计算机系）；Institute of Health Informatics, University College London（伦敦大学学院健康信息学研究所）；Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（上海智能自主系统研究所，同济大学）；College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院）；University College London Hospital（伦敦大学学院医院）
Anonymous networks have enabled secure and anonymous communication between the users and service providers while maintaining their anonymity and privacy. The hidden services in the networks are dynamic and continuously change their domains and service features to maintain anonymity and prevent fingerprinting. This makes modelling of such networks a challenging task. Further, modelling with crisp graphs is not suitable as they cannot capture the dynamic nature of the anonymous networks. In this work, we model the anonymous networks using fuzzy graphs and provide a methodology to simulate and an…
Columbia University（哥伦比亚大学）；Virginia Tech（弗吉尼亚理工大学）；Google Research（谷歌研究院）
Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying differential privacy (DP), a canonical notion with provable privacy guarantees for machine learning models, to those models remains challenging due to the trade-off between model utility and privacy loss. Utilizing the fact that sensitive information in language data tends to be sparse, Shi et al. (2021) formalized a DP notion extension called Selective Differential Privacy (SDP) to protect only the sensitive tokens defined by a policy function. H…
The creation and maintenance of a Register of Processing Activities (ROPA) is an essential process for the demonstration of GDPR compliance. We analyse ROPA templates from six EU Data Protection Regulators and show that template scope and granularity vary widely between jurisdictions. We then propose a flexible, consolidated data model for consistent processing of ROPAs (CSM-ROPA). We analyse the extent that the Data Privacy Vocabulary (DPV) can be used to express CSM-ROPA. We find that it does not directly address modelling ROPAs, and so needs additional concept definitions. We provide a mapp…
We present two new statistical machine learning methods designed to learn on fully homomorphic encrypted (FHE) data. The introduction of FHE schemes following Gentry (2009) opens up the prospect of privacy preserving statistical machine learning analysis and modelling of encrypted data without compromising security constraints. We propose tailored algorithms for applying extremely random forests, involving a new cryptographic stochastic fraction estimator, and naïve Bayes, involving a semi-parametric model for the class decision boundary, and show how they can be used to learn and predict from…
Graph Neural Networks (GNNs) are a popular technique for modelling graph-structured data and computing node-level representations via aggregation of information from the neighborhood of each node. However, this aggregation implies an increased risk of revealing sensitive information, as a node can participate in the inference for multiple nodes. This implies that standard privacy-preserving machine learning techniques, such as differentially private stochastic gradient descent (DP-SGD) - which are designed for situations where each data point participates in the inference for one point only - …
Aalto University（阿尔托大学）；NVIDIA AI Technology Center（英伟达人工智能技术中心）；University of Manchester（曼彻斯特大学）；University of Helsinki（赫尔辛基大学）
We present d3p, a software package designed to help fielding runtime efficient widely-applicable Bayesian inference under differential privacy guarantees. d3p achieves general applicability to a wide range of probabilistic modelling problems by implementing the differentially private variational inference algorithm, allowing users to fit any parametric probabilistic model with a differentiable density function. d3p adopts the probabilistic programming paradigm as a powerful way for the user to flexibly define such models. We demonstrate the use of our software on a hierarchical logistic regres…
Despite increasing uptake, there are still many concerns as to the security of virtual assistant hubs (such as Google Nest and Amazon Alexa) in the home. Consumer fears have been somewhat exacerbated by widely-publicised privacy breaches, and the continued prevalence of high-profile attacks targeting IoT networks. Literature suggests a considerable knowledge gap between consumer understanding and the actual threat environment; furthermore, little work has been done to compare which threat modelling approach(es) would be most appropriate for these devices, in order to elucidate the threats whic…
Speech data on the Internet are proliferating exponentially because of the emergence of social media, and the sharing of such personal data raises obvious security and privacy concerns. One solution to mitigate these concerns involves concealing speaker identities before sharing speech data, also referred to as speaker anonymization. In our previous work, we have developed an automatic speaker verification (ASV)-model-free anonymization framework to protect speaker privacy while preserving speech intelligibility. Although the framework ranked first place in VoicePrivacy 2022 challenge, the ano…
In this paper we address the issue of gathering the "informed consent" of an end user in the Internet of Things. We start by evaluating the legal importance and some of the problems linked with this notion of informed consent in the specific context of the Internet of Things. From this assessment we propose an approach based on a semi-autonomous, rule based agent that centralize all authorization decisions on the personal data of a user and that is able to take decision on his behalf. We complete this initial agent by integrating context-awareness, behavior modeling and community based reputat…
Technical University of Munich（慕尼黑工业大学）；OpenMined；Imperial College London（帝国理工学院）
In recent years, formal methods of privacy protection such as differential privacy (DP), capable of deployment to data-driven tasks such as machine learning (ML), have emerged. Reconciling large-scale ML with the closed-form reasoning required for the principled analysis of individual privacy loss requires the introduction of new tools for automatic sensitivity analysis and for tracking an individual's data and their features through the flow of computation. For this purpose, we introduce a novel \textit{hybrid} automatic differentiation (AD) system which combines the efficiency of reverse-mod…
Tsinghua University（清华大学）；Max-Planck-Institut für Quantenoptik（马克斯·普朗克量子光学研究所）；Shanghai Qi Zhi Institute（上海期智研究院）
Private distributed learning studies the problem of how multiple distributed entities collaboratively train a shared deep network with their private data unrevealed. With the security provided by the protocols of blind quantum computation, the cooperation between quantum physics and machine learning may lead to unparalleled prospect for solving private distributed learning tasks. In this paper, we introduce a quantum protocol for distributed learning that is able to utilize the computational power of the remote quantum servers while keeping the private data safe. For concreteness, we first int…
"My sex-related data is more sensitive than my financial data and I want the same level of security and privacy": User Risk Perceptions and Protective Actions in Female-oriented Technologies
