Related papers: Towards Practical Privacy-Preserving Solution for …

We present a practical framework to deploy privacy-preserving machine learning (PPML) applications in untrusted clouds based on a trusted execution environment (TEE). Specifically, we shield unmodified PyTorch ML applications by running…

With the increasing popularity of Internet of Things (IoT) devices, securing sensitive user data has emerged as a major challenge. These devices often collect confidential information, such as audio and visual data, through peripheral…

With the increasing popularity of Internet of Things (IoT) devices, security concerns have become a major challenge: confidential information is constantly being transmitted (sometimes inadvertently) from user devices to untrusted cloud…

The majority of financial organizations managing confidential data are aware of security threats and leverage widely accepted solutions (e.g., storage encryption, transport-level encryption, intrusion detection systems) to prevent or detect…

Deploying large language models (LLMs) in real-time systems remains challenging due to their substantial computational demands and privacy concerns. We propose Floe, a hybrid federated learning framework designed for latency-sensitive,…

The use of Neural Networks (NNs) for sensitive data processing is becoming increasingly popular, raising concerns about data privacy and security. Homomorphic Encryption (HE) has the potential to be used as a solution to preserve data…

Cloud computing is emerging as a revolutionary computing paradigm, while security and privacy become major concerns in the cloud scenario. For which Searchable Encryption (SE) technology is proposed to support efficient retrieval of…

This work addresses the timely yet underexplored problem of performing inference and finetuning of a proprietary LLM owned by a model provider entity on the confidential/private data of another data owner entity, in a way that ensures the…

Federated Learning trains machine learning models on distributed devices by aggregating local model updates instead of local data. However, privacy concerns arise as the aggregated local models on the server may reveal sensitive personal…

Federated Learning (FL) enables collaborative training while keeping sensitive data on clients' devices, but local model updates can still leak private information. Hybrid Homomorphic Encryption (HHE) has recently been applied to FL to…

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial…

The problem we address is the following: how can a user employ a predictive model that is held by a third party, without compromising private information. For example, a hospital may wish to use a cloud service to predict the readmission…

Oblivious inference is the task of outsourcing a ML model, like neural-networks, without disclosing critical and sensitive information, like the model's parameters. One of the most prominent solutions for secure oblivious inference is based…

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while…

Convolutional neural network is a machine-learning model widely applied in various prediction tasks, such as computer vision and medical image analysis. Their great predictive power requires extensive computation, which encourages model…

To safeguard user data privacy, on-device inference has emerged as a prominent paradigm on mobile and Internet of Things (IoT) devices. This paradigm involves deploying a model provided by a third party on local devices to perform inference…

We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones…

While the security of the cloud remains a concern, a common practice is to encrypt data before outsourcing them for utilization. One key challenging issue is how to efficiently perform queries over the ciphertext. Conventional crypto-based…

Fully Homomorphic Encryption (FHE) allows for computation directly on encrypted data and enables privacy-preserving neural inference in the cloud. Prior work has focused on models with dense inputs (e.g., CNNs), with less attention given to…

The widespread adoption of Machine Learning as a Service raises critical privacy and security concerns, particularly about data confidentiality and trust in both cloud providers and the machine learning models. Homomorphic Encryption (HE)…