Related papers: DarKnight: An Accelerated Framework for Privacy an…

Secure computation is of critical importance to not only the DoD, but across financial institutions, healthcare, and anywhere personally identifiable information (PII) is accessed. Traditional security techniques require data to be…

Deep learning models leak significant amounts of information about their training datasets. Previous work has investigated training models with differential privacy (DP) guarantees through adding DP noise to the gradients. However, such…

There is an urgent demand for privacy-preserving techniques capable of supporting compute and data intensive (CDI) computing in the era of big data. However, none of existing TEEs can truly support CDI computing tasks, as CDI requires high…

Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML's pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential…

Federated learning is considered as an effective privacy-preserving learning mechanism that separates the client's data and model training process. However, federated learning is still under the risk of privacy leakage because of the…

Machine Learning as a Service (MLaaS) has become a growing trend in recent years and several such services are currently offered. MLaaS is essentially a set of services that provides machine learning tools and capabilities as part of cloud…

The rapid deployment of deep neural network (DNN) accelerators in safety-critical domains such as autonomous vehicles, healthcare systems, and financial infrastructure necessitates robust mechanisms to safeguard data confidentiality and…

Deep learning-based face recognition (FR) systems pose significant privacy risks by tracking users without their consent. While adversarial attacks can protect privacy, they often produce visible artifacts compromising user experience. To…

Data privacy concerns often prevent the use of cloud-based machine learning services for sensitive personal data. While homomorphic encryption (HE) offers a potential solution by enabling computations on encrypted data, the challenge is to…

This study identifies and proposes techniques to alleviate two key bottlenecks to executing deep neural networks in trusted execution environments (TEEs): page thrashing during the execution of convolutional layers and the decryption of…

Federated learning is a distributed learning method to train a shared model by aggregating the locally-computed gradient updates. In federated learning, bandwidth and privacy are two main concerns of gradient updates transmission. This…

An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of…

The increasing adoption of Large Language Models (LLMs) in cloud environments raises critical security concerns, particularly regarding model confidentiality and data privacy. Confidential computing, enabled by Trusted Execution…

This report evaluates the performance impact of enabling Trusted Execution Environments (TEE) on NVIDIA Hopper GPUs for large language model (LLM) inference tasks. We benchmark the overhead introduced by TEE mode across various LLMs and…

Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information. Most privacy-preserving methods lead to undesirable performance…

Graph Neural Networks (GNNs) have marked significant impact in traffic state prediction, social recommendation, knowledge-aware question answering and so on. As more and more users move towards cloud computing, it has become a critical…

Distributed collaborative learning (DCL) paradigms enable building joint machine learning models from distrusting multi-party participants. Data confidentiality is guaranteed by retaining private training data on each participant's local…

In the era of cloud computing and data-driven applications, it is crucial to protect sensitive information to maintain data privacy, ensuring truly reliable systems. As a result, preserving privacy in deep learning systems has become a…

Although Deep Neural Networks (DNN) have become the backbone technology of several ubiquitous applications, their deployment in resource-constrained machines, e.g., Internet of Things (IoT) devices, is still challenging. To satisfy the…

Privacy is a crucial concern in collaborative machine vision where a part of a Deep Neural network (DNN) model runs on the edge, and the rest is executed on the cloud. In such applications, the machine vision model does not need the exact…