Related papers: DynSGX: A Privacy Preserving Toolset for Dynamical…

Cloud-edge collaborative inference approach splits deep neural networks (DNNs) into two parts that run collaboratively on resource-constrained edge devices and cloud servers, aiming at minimizing inference latency and protecting data…

Many applications benefit from computations over the data of multiple users while preserving confidentiality. We present a solution where multiple mutually distrusting users' data can be aggregated with an acceptable overhead, while…

The Deep Leakage from Gradient (DLG) attack has emerged as a prevalent and highly effective method for extracting sensitive training data by inspecting exchanged gradients. This approach poses a substantial threat to the privacy of…

Deep learning as a service (DLaaS) has been intensively studied to facilitate the wider deployment of the emerging deep learning applications. However, DLaaS may compromise the privacy of both clients and cloud servers. Although some…

While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential privacy (DP) on sensitive data can sidestep this challenge,…

Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…

Stream processing systems are important in modern applications in which data arrive continuously and need to be processed in real time. Because of their resource and scalability requirements, many of these systems run on the cloud, which is…

Differential privacy is a useful tool to build machine learning models which do not release too much information about the training data. We study the R\'enyi differential privacy of stochastic gradient descent when each training example is…

We introduce a new timing side-channel attack on Intel CPU processors. Our Frontal attack exploits timing differences that arise from how the CPU frontend fetches and processes instructions while being interrupted. In particular, we observe…

Privacy regulation laws, such as GDPR, impose transparency and security as design pillars for data processing algorithms. In this context, federated learning is one of the most influential frameworks for privacy-preserving distributed…

Enclave deployments often fail to simultaneously be secure (e.g., resistant to side channel attacks), powerful (i.e., as fast as an off-the-shelf server), and flexible (i.e., unconstrained by development hurdles). In this paper, we present…

Deep Neural Network (DNN), one of the most powerful machine learning algorithms, is increasingly leveraged to overcome the bottleneck of effectively exploring and analyzing massive data to boost advanced scientific development. It is not a…

In the realm of power systems, the increasing involvement of residential users in load forecasting applications has heightened concerns about data privacy. Specifically, the load data can inadvertently reveal the daily routines of…

Deep Neural Network (DNN) has been showing great potential in kinds of real-world applications such as fraud detection and distress prediction. Meanwhile, data isolation has become a serious problem currently, i.e., different parties cannot…

This work introduces a GPU storage expansion solution utilizing CXL, featuring a novel GPU system design with multiple CXL root ports for integrating diverse storage media (DRAMs and/or SSDs). We developed and siliconized a custom CXL…

Trusted Execution Environments (TEEs) suffer from performance issues when executing certain management instructions, such as creating an enclave, context switching in and out of protected mode, and swapping cached pages. This is especially…

Differentially private training offers a protection which is usually interpreted as a guarantee against membership inference attacks. By proxy, this guarantee extends to other threats like reconstruction attacks attempting to extract…

The advent of location-based services has led to the widespread adoption of indoor localization systems, which enable location tracking of individuals within enclosed spaces such as buildings. While these systems provide numerous benefits…

This paper considers the scenario that multiple data owners wish to apply a machine learning method over the combined dataset of all owners to obtain the best possible learning output but do not want to share the local datasets owing to…

Privileged malware neutralizes software-based versioning systems and destroys data. To counter this threat, a versioning solid-state drive (SSD) that performs versioning inside the SSD has been studied. An SSD is a suitable candidate for…