Related papers: TETRIS: Composing FHE Techniques for Private Funct…

We develop theory for using heuristics to solve computationally hard problems in differential privacy. Heuristic approaches have enjoyed tremendous success in machine learning, for which performance can be empirically evaluated. However,…

The database community, at least for the last decade, has been grappling with querying encrypted data, which would enable secure database as a service solutions. A recent breakthrough in the cryptographic community (in 2009) related to…

Transfer learning is a de facto standard method for efficiently training machine learning models for data-scarce problems by adding and fine-tuning new classification layers to a model pre-trained on large datasets. Although numerous…

Medical image classification plays a crucial role in computer-aided clinical diagnosis. While deep learning techniques have significantly enhanced efficiency and reduced costs, the privacy-sensitive nature of medical imaging data…

The average treatment effect (ATE) is widely used to evaluate the effectiveness of drugs and other medical interventions. In safety-critical applications like medicine, reliable inferences about the ATE typically require valid uncertainty…

Privacy-preserving machine learning (PPML) has become increasingly important in applications where sensitive data must remain confidential. Homomorphic Encryption (HE) enables computation directly on encrypted data, allowing neural network…

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…

Fully homomorphic encryption allows the evaluation of arbitrary functions on encrypted data. It can be leveraged to secure outsourced and multiparty computation. TFHE is a fast torus-based fully homomorphic encryption scheme that allows…

Existing approaches to protect the privacy of Electronic Health Records are either insufficient for existing medical laws or they are too restrictive in their usage. For example, smart card-based encryption systems require the patient to be…

Federated Trajectory Matching (FTM) is gaining increasing importance in big trajectory data analytics, supporting diverse applications such as public health, law enforcement, and emergency response. FTM retrieves trajectories that match…

E-health record (EHR) contains a vast amount of continuously growing medical data and enables medical institutions to access patient health data conveniently.This provides opportunities for medical data mining which has important…

Introduction: The amount of data generated by original research is growing exponentially. Publicly releasing them is recommended to comply with the Open Science principles. However, data collected from human participants cannot be released…

Ensuring resilience to Byzantine clients while maintaining the privacy of the clients' data is a fundamental challenge in federated learning (FL). When the clients' data is homogeneous, suitable countermeasures were studied from an…

Healthcare data contains some of the most sensitive information about an individual, yet sharing this data with healthcare practitioners can significantly enhance patient care and support research efforts. However, current systems for…

With the popularity of cloud computing and machine learning, it has been a trend to outsource machine learning processes (including model training and model-based inference) to cloud. By the outsourcing, other than utilizing the extensive…

Training data is fundamental to the success of modern machine learning models, yet in high-stakes domains such as healthcare, the use of real-world training data is severely constrained by concerns over privacy leakage. A promising solution…

Privacy-preserving machine learning has become an important long-term pursuit in this era of artificial intelligence (AI). Fully Homomorphic Encryption (FHE) is a uniquely promising solution, offering provable privacy and security…

Homomorphic encryption (HE) is a promising technique used for privacy-preserving computation. Since HE schemes only support primitive polynomial operations, homomorphic evaluation of polynomial approximations for non-polynomial functions…

Edge computing alleviates the computation burden of data-driven control in cyber-physical systems (CPSs) by offloading complex processing to edge servers. However, the increasing sophistication of cyberattacks underscores the need for…

In Federated Learning (FL), accessing private client data incurs communication and privacy costs. As a result, FL deployments commonly prefinetune pretrained foundation models on a (large, possibly public) dataset that is held by the…