相关论文: AgEncID: Aggregate Encryption Individual Decryptio…

Semiconductor design houses rely on third-party foundries to manufacture their integrated circuits (IC). While this trend allows them to tackle fabrication costs, it introduces security concerns as external (and potentially malicious)…

Secure aggregation, which is a core component of federated learning, aggregates locally trained models from distributed users at a central server. The ``secure'' nature of such aggregation consists of the fact that no information about the…

Federated learning (FL) enables collaborative model training by aggregating local updates without requiring raw data sharing. However, prior studies have shown that servers can exploit gradient inversion to compromise user privacy or…

Computational privacy is a property of cryptographic system that ensures the privacy of data being processed at an untrusted server. Fully Homomorphic Encryption Schemes (FHE) promise to provide such property. Contemporary FHE schemes are…

We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Locally differentially private algorithms require little trust but are (provably) limited…

Processing data received as a stream is a task commonly performed by modern embedded devices, in a wide range of applications such as multimedia (encoding/decoding/ playing media), networking (switching and routing), digital security,…

This paper presents a system consisting of the FPGA IP core, the simple network protocol and the Linux device driver, capable of efficient and reliable data transmission from a low resources FPGA chip to the Linux-based embedded computer…

Medical health care centers are envisioned as a promising paradigm to handle the massive volume of data of COVID-19 patients using artificial intelligence (AI). Traditionally, AI techniques often require centralized data collection and…

Federated Learning (FL) is a promising distributed learning framework designed for privacy-aware applications. FL trains models on client devices without sharing the client's data and generates a global model on a server by aggregating…

Federated Learning has rapidly expanded from its original inception to now have a large body of research, several frameworks, and sold in a variety of commercial offerings. Thus, its security and robustness is of significant importance.…

In recent years, edge computing (EC) has attracted great attention for its high-speed computing and low-latency characteristics. However, there are many challenges in the implementation of EC. Firstly, user's privacy has been raised as a…

To address the risks of increasingly capable AI systems, we introduce a hardware-level off-switch that embeds thousands of independent "security blocks" in each AI accelerator. This massively redundant architecture is designed to prevent…

In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model. To address the risk of exposing sensitive data through local models, secure…

Field Programmable Gate Arrays (FPGAs) are increasingly in various applications. This is due to the fact that they provide flexibility to reprogram and modify in realtime with minimum effort. The increasing usage of FPGA must also ensure…

Cryptanalysis of block ciphers involves massive computations which are independent of each other and can be instantiated simultaneously so that the solution space is explored at a faster rate. With the advent of low cost Field Programmable…

This paper proposes a blockchain-based Federated Learning (FL) framework with Intel Software Guard Extension (SGX)-based Trusted Execution Environment (TEE) to securely aggregate local models in Industrial Internet-of-Things (IIoTs). In FL,…

With the ever-growing demand for cybersecurity, static key encryption mechanisms are increasingly vulnerable to adversarial attacks due to their deterministic and non-adaptive nature. Brute-force attacks, key compromise, and unauthorized…

FHE offers protection to private data on third-party cloud servers by allowing computations on the data in encrypted form. However, to support general-purpose encrypted computations, all existing FHE schemes require an expensive operation…

Cryptographic schemes like Fully Homomorphic Encryption (FHE) and Zero-Knowledge Proofs (ZKPs), while offering powerful privacy-preserving capabilities, are often hindered by their computational complexity. Polynomial multiplication, a core…

Recent research in Internet of things has been widely applied for industrial practices, fostering the exponential growth of data and connected devices. Henceforth, data-driven AI models would be accessed by different parties through certain…