Related papers: Spatial Privacy-aware VR streaming
Differentially private (DP) stochastic convex optimization (SCO) is ubiquitous in trustworthy machine learning algorithm design. This paper studies the DP-SCO problem with streaming data sampled from a distribution and arrives sequentially.…
The concept of differential privacy (DP) can quantitatively measure privacy loss by observing the changes in the distribution caused by the inclusion of individuals in the target dataset. The DP, which is generally used as a constraint, has…
Over the past decade, programmatic advertising has received a great deal of attention in the online advertising industry. A real-time bidding (RTB) system is rapidly becoming the most popular method to buy and sell online advertising…
Differential privacy is the state-of-the-art definition for privacy, guaranteeing that any analysis performed on a sensitive dataset leaks no information about the individuals whose data are contained therein. In this thesis, we develop…
Collaborative training of neural networks leverages distributed data by exchanging gradient information between different clients. Although training data entirely resides with the clients, recent work shows that training data can be…
Nowadays, machine learning models and applications have become increasingly pervasive. With this rapid increase in the development and employment of machine learning models, a concern regarding privacy has risen. Thus, there is a legitimate…
Abrupt resolution changes in virtual reality (VR) streaming can significantly impair the quality-of-experience (QoE) of users, particularly during transitions from high to low resolutions. Existing QoE models and transmission schemes…
360{\deg} video is attracting an increasing amount of attention in the context of Virtual Reality (VR). Owing to its very high-resolution requirements, existing professional streaming services for 360{\deg} video suffer from severe…
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…
Inferring the quality of network services is the vital basis of optimization for network operators. However, prevailing real-time video streaming applications adopt encryption for security, leaving it a problem to extract Quality of Service…
Quantum computing has been widely applied in various fields, such as quantum physics simulations, quantum machine learning, and big data analysis. However, in the domains of data-driven paradigm, how to ensure the privacy of the database is…
Learning a privacy-preserving model from sensitive data which are distributed across multiple devices is an increasingly important problem. The problem is often formulated in the federated learning context, with the aim of learning a single…
Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator…
Virtual reality has been gaining popularity in recent years caused by the proliferation of affordable consumer-grade devices such as Oculus Rift, HTC Vive, and Samsung VR. Amongst the various VR applications, 360{\deg} video streaming is…
The protection of sensitive data becomes more vital, as data increases in value and potency. Furthermore, the pressure increases from regulators and society on model developers to make their Artificial Intelligence (AI) models…
Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user data, which could lead to significant privacy concerns when…
Recently, there has been an increasing adoption of differential privacy guided algorithms for privacy-preserving machine learning tasks. However, the use of such algorithms comes with trade-offs in terms of algorithmic fairness, which has…
Objective perturbation is a standard mechanism in differentially private empirical risk minimization. In particular, Linear Objective Perturbation (LOP) enforces privacy by adding a random linear term, while strong convexity and stability…
We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relying on multiparty homomorphic encryption. RHODE preserves the…
Recommender systems are an integral part of online platforms that recommend new content to users with similar interests. However, they demand a considerable amount of user activity data where, if the data is not adequately protected,…