Related papers: Towards Anonymous Neural Network Inference
We present HORNET, a system that enables high-speed end-to-end anonymous channels by leveraging next generation network architectures. HORNET is designed as a low-latency onion routing system that operates at the network layer thus enabling…
User-facing software services are becoming increasingly reliant on remote servers to host Deep Neural Network (DNN) models, which perform inference tasks for the clients. Such services require the client to send input data to the service…
This study investigates the potential for deanonymizing services within the Invisible Internet Project (I2P) network through passive traffic analysis and machine learning techniques. The primary objective is to identify distinctive patterns…
With the rapid advancement of AI technology, we have seen more and more concerns on data privacy, leading to some cutting-edge research on machine learning with encrypted computation. Fully Homomorphic Encryption (FHE) is a crucial…
Fully Homomorphic Encryption (FHE) allows computations to be performed directly on encrypted data without needing to decrypt it first. This "encryption-in-use" feature is crucial for securely outsourcing computations in privacy-sensitive…
Federated learning promises to make machine learning feasible on distributed, private datasets by implementing gradient descent using secure aggregation methods. The idea is to compute a global weight update without revealing the…
Caching aims to store data locally in some nodes within the network to be able to retrieve the contents in shorter time periods. However, caching in the network did not always consider secure storage (due to the compromise between time…
We present Fission, a new permissionless blockchain that achieves scalability in both terms of system throughput and transaction confirmation time, while at the same time, retaining blockchain's core values of equality and decentralization.…
Physical Unclonable Functions (PUFs) have been shown to be a highly promising solution for enabling high security systems tailored for low-power devices. Commonly, PUFs are utilised to generate cryptographic keys on-the-fly, replacing the…
Recent work on stealing machine learning (ML) models from inference engines with physical side-channel attacks warrant an urgent need for effective side-channel defenses. This work proposes the first $\textit{fully-masked}$ neural network…
Deep neural network (DNN)-based joint source and channel coding is proposed for privacy-aware end-to-end image transmission against multiple eavesdroppers. Both scenarios of colluding and non-colluding eavesdroppers are considered. Unlike…
Privacy is a major concern in designing any cryptographic primitive when frequent transactions are done electronically. During electronic transactions, people reveal their personal data into several servers and believe that this information…
Current security techniques can be implemented with either secret key exchange or physical layer wiretap codes. In this work, we investigate an alternative solution for MIMO wiretap channels. Inspired by the artificial noise (AN) technique,…
Privacy-preserving Transformer inference has gained attention due to the potential leakage of private information. Despite recent progress, existing frameworks still fall short of practical model scales, with gaps up to a hundredfold. A…
Oblivious inference is the task of outsourcing a ML model, like neural-networks, without disclosing critical and sensitive information, like the model's parameters. One of the most prominent solutions for secure oblivious inference is based…
We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art of private deep learning…
Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources, which drives their popularity across various applications. Recent studies highlight the potential of mapping BNN model…
Anonymous credentials (ACs) are a crucial cryptographic tool for privacy-preserving authentication in decentralized networks, allowing holders to prove eligibility without revealing their identity. However, a major limitation of standard…
Hosted large language models are increasingly accessed through remote APIs, but the API boundary still offers little direct evidence that a returned output actually corresponds to the client-visible request. Recent audits of shadow APIs…
Machine learning has revolutionized data analysis and pattern recognition, but its resource-intensive training has limited accessibility. Machine Learning as a Service (MLaaS) simplifies this by enabling users to delegate their data samples…