Related papers: Network and Compiler Optimizations for Efficient L…

Quantum homomorphic encryption (QHE), allows a quantum cloud server to compute on private data as uploaded by a client. We provide a proof-of-concept software simulation for QHE, according to the "EPR" scheme of Broadbent and Jeffery, for…

Much of machine learning relies on the use of large amounts of data to train models to make predictions. When this data comes from multiple sources, for example when evaluation of data against a machine learning model is offered as a…

Fully Homomorphic Encryption (FHE) enables the evaluation of programs directly on encrypted data. However, because only basic operations can be performed on ciphertexts, programs must be expressed as boolean or arithmetic circuits. This…

Performing smart computations in a context of cloud computing and big data is highly appreciated today. Fully homomorphic encryption (FHE) is a smart category of encryption schemes that allows working with the data in its encrypted form. It…

Homomorphic encryption enables computations on encrypted data without accessing private keys, enhancing security in cloud environments. Without this technology, updates need to be performed on-premises or require transmitting private keys…

Large scale deep learning model, such as modern language models and diffusion architectures, have revolutionized applications ranging from natural language processing to computer vision. However, their deployment in distributed or…

Preserving data confidentiality during the fine-tuning of open-source Large Language Models (LLMs) is crucial for sensitive applications. This work introduces an interactive protocol adapting the Low-Rank Adaptation (LoRA) technique for…

Fully Homomorphic Encryption (FHE) enables the processing of encrypted data without decrypting it. FHE has garnered significant attention over the past decade as it supports secure outsourcing of data processing to remote cloud services.…

Fully Homomorphic Encryption (FHE) enables privacy-preserving Transformer inference, but long-sequence encrypted Transformers quickly exceed single-GPU memory capacity because encoded weights are already large and encrypted activations grow…

With the advent of functional encryption, new possibilities for computation on encrypted data have arisen. Functional Encryption enables data owners to grant third-party access to perform specified computations without disclosing their…

Private Transformer inference using cryptographic protocols offers promising solutions for privacy-preserving machine learning; however, it still faces significant runtime overhead (efficiency issues) and challenges in handling long-token…

Machine Learning (ML) has emerged as one of data science's most transformative and influential domains. However, the widespread adoption of ML introduces privacy-related concerns owing to the increasing number of malicious attacks targeting…

With the rapid advancements in machine learning, models have become increasingly capable of learning and making predictions in various industries. However, deploying these models in critical infrastructures presents a major challenge, as…

Modern cloud inference creates a two sided privacy problem where users reveal sensitive inputs to providers, while providers must execute proprietary model weights inside potentially leaky execution environments. Fully homomorphic…

Fully Homomorphic Encryption (FHE), a novel cryptographic theory enabling computation directly on ciphertext data, offers significant security benefits but is hampered by substantial performance overhead. In recent years, a series of…

In today's machine learning landscape, fine-tuning pretrained transformer models has emerged as an essential technique, particularly in scenarios where access to task-aligned training data is limited. However, challenges surface when data…

Quantum homomorphic encryption (QHE) is an encryption method that allows quantum computation to be performed on one party's private data with the program provided by another party, without revealing much information about the data nor the…

Federated learning has become increasingly widespread due to its ability to train models collaboratively without centralizing sensitive data. While most research on FL emphasizes privacy-preserving techniques during training, the evaluation…

Biometric matching involves storing and processing sensitive user information. Maintaining the privacy of this data is thus a major challenge, and homomorphic encryption offers a possible solution. We propose a privacy-preserving…

Quantum machine learning in cloud environments requires protecting sensitive data while enabling remote computation. Here we demonstrate the first realistic implementations of a perfectly-secure quantum homomorphic encryption (QHE) scheme…