Related papers: Highly Scalable Beaver Triple Generator from Addit…

Machine learning on encrypted data can address the concerns related to privacy and legality of sharing sensitive data with untrustworthy service providers. Fully Homomorphic Encryption (FHE) is a promising technique to enable machine…

Machine learning (ML) is widely used today, especially through deep neural networks (DNNs), however, increasing computational load and resource requirements have led to cloud-based solutions. To address this problem, a new generation of…

In contemporary cloud-based services, protecting users' sensitive data and ensuring the confidentiality of the server's model are critical. Fully homomorphic encryption (FHE) enables inference directly on encrypted inputs, but its…

Multi-Key Homomorphic Encryption (MKHE), proposed by Lopez-Alt et al. (STOC 2012), allows for performing arithmetic computations directly on ciphertexts encrypted under distinct keys. Subsequent works by Chen and Dai et al. (CCS 2019) and…

With the ubiquitous deployment of web services, ensuring data confidentiality has become a challenging imperative. Fully Homomorphic Encryption (FHE) presents a powerful solution for processing encrypted data; however, its widespread…

Federated machine learning leverages edge computing to develop models from network user data, but privacy in federated learning remains a major challenge. Techniques using differential privacy have been proposed to address this, but bring…

The rapid adoption of chiplet-based heterogeneous integration is reshaping semiconductor design by enabling modular, scalable, and faster time-to-market solutions for AI and high-performance computing. However, multi-vendor assembly in…

Fully Homomorphic Encryption (FHE) allows arbitrarily complex computations on encrypted data without ever needing to decrypt it, thus enabling us to maintain data privacy on third-party systems. Unfortunately, sustaining deep computations…

Deep learning (DL) approaches are achieving extraordinary results in a wide range of domains, but often require a massive collection of private data. Hence, methods for training neural networks on the joint data of different data owners,…

The growing body of literature on training-data reconstruction attacks raises significant concerns about deploying neural network classifiers trained on sensitive data. However, differentially private (DP) training (e.g. using DP-SGD) can…

Bilinear groups are often used to create Attribute-Based Encryption (ABE) algorithms. In particular, they have been used to create an ABE system with multi authorities, but limited to the ciphertext-policy instance. Here, for the first…

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…

Privacy-preserving deep learning addresses privacy concerns in Machine Learning as a Service (MLaaS) by using Homomorphic Encryption (HE) for linear computations. However, the computational overhead remains a major challenge. While prior…

Secure multi-party computation-based machine learning, referred to as MPL, has become an important technology to utilize data from multiple parties with privacy preservation. While MPL provides rigorous security guarantees for the…

Homomorphic encryption (HE) is a privacy-preserving technique that enables computation directly on encrypted data. Despite its promise, HE has seen limited use due to performance overheads and compilation challenges. Recent work has made…

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…

Large language model (LLM) based services are primarily structured as client-server interactions, with clients sending queries directly to cloud providers that host LLMs. This approach currently compromises data privacy as all queries must…

Federated Learning is a well-researched approach for collaboratively training machine learning models across decentralized data while preserving privacy. However, integrating Homomorphic Encryption to ensure data confidentiality introduces…

Homomorphic encryption (HE) enables computations on encrypted data by concealing information under noise for security. However, the process of bootstrapping, which resets the noise level in the ciphertext, is computationally expensive and…

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…