Related papers: DCT-CryptoNets: Scaling Private Inference in the F…

Fully Homomorphic Encryption (FHE) is a cryptographic method that guarantees the privacy and security of user data during computation. FHE algorithms can perform unlimited arithmetic computations directly on encrypted data without…

Designing privacy-preserving deep learning models is a major challenge within the deep learning community. Homomorphic Encryption (HE) has emerged as one of the most promising approaches in this realm, enabling the decoupling of knowledge…

Audio and speech data are increasingly used in machine learning applications such as speech recognition, speaker identification, and mental health monitoring. However, the passive collection of this data by audio listening devices raises…

The demand for processing vast volumes of data has surged dramatically due to the advancement of machine learning technology. Large-scale data processing necessitates substantial computational resources, prompting individuals and…

Big data is one of the cornerstones to enabling and training deep neural networks (DNNs). Because of the lack of expertise, to gain benefits from their data, average users have to rely on and upload their private data to big data companies…

Publicly available large pretrained models (i.e., backbones) and lightweight adapters for parameter-efficient fine-tuning (PEFT) have become standard components in modern machine learning pipelines. However, preserving the privacy of both…

Homomorphic encryption (HE) is a privacy-preserving technique that enables computation directly over ciphertext. Unfortunately, a key challenge for HE is that implementations can be impractically slow and have limits on computation that can…

The privacy concerns of providing deep learning inference as a service have underscored the need for private inference (PI) protocols that protect users' data and the service provider's model using cryptographic methods. Recently proposed…

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…

This paper explores image modeling from the frequency space and introduces DCTdiff, an end-to-end diffusion generative paradigm that efficiently models images in the discrete cosine transform (DCT) space. We investigate the design space of…

As machine learning as a service continues gaining popularity, concerns about privacy and intellectual property arise. Users often hesitate to disclose their private information to obtain a service, while service providers aim to protect…

We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers updated locally using private data and to ensure that no…

Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as…

The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity. Inference of uncompressed large scale DNN models…

The discrete cosine transform (DCT) is a relevant tool in signal processing applications, mainly known for its good decorrelation properties. Current image and video coding standards -- such as JPEG and HEVC -- adopt the DCT as a…

In this paper, a secure Convolutional Neural Network classifier is proposed using Fully Homomorphic Encryption (FHE). The secure classifier provides a user with the ability to out-source the computations to a powerful cloud server and/or…

Graph Convolutional Neural Networks (GCNs) have gained widespread popularity in various fields like personal healthcare and financial systems, due to their remarkable performance. Despite the growing demand for cloud-based GCN services,…

With the rapid increase in cloud computing, concerns surrounding data privacy, security, and confidentiality also have been increased significantly. Not only cloud providers are susceptible to internal and external hacks, but also in some…

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…

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…