Related papers: Secure Transformer Inference Protocol
A fully homomorphic encryption system hides data from unauthorized parties, while still allowing them to perform computations on the encrypted data. Aside from the straightforward benefit of allowing users to delegate computations to a more…
Efficient multi-party secure matrix multiplication is crucial for privacy-preserving machine learning, but existing mixed-protocol frameworks often face challenges in balancing security, efficiency, and accuracy. This paper presents an…
Multi-party private set union (MPSU) protocol enables $m$ $(m > 2)$ parties, each holding a set, to collectively compute the union of their sets without revealing any additional information to other parties. There are two main categories of…
The rapid development of cloud computing has probably benefited each of us. However, the privacy risks brought by untrustworthy cloud servers arise the attention of more and more people and legislatures. In the last two decades, plenty of…
ML-as-a-service continues to grow, and so does the need for very strong privacy guarantees. Secure inference has emerged as a potential solution, wherein cryptographic primitives allow inference without revealing users' inputs to a model…
In this study, we propose PRETRUST, a new framework to address the problem of the efficiency of payment process based on blockchain systems. PRETRUST is based on the thoughts of consortium chains, supporting fast payments. To make parties…
Oblivious transfer is an important primitive in modern cryptography. Applications include secure multiparty computation, oblivious sampling, e-voting, and signatures. Information-theoretically secure perfect 1-out-of 2 oblivious transfer is…
The Stream Control Transmission Protocol (SCTP) is a Transport Layer protocol that has been proposed as an alternative to the Transmission Control Protocol (TCP) for the Internet of Things (IoT). SCTP, with its four-way handshake mechanism,…
We propose an efficient quantum protocol performing quantum bit commitment, which is a simple cryptographic primitive involved with two parties, called a committer and a verifier. Our protocol is non-interactive, uses no supplemental shared…
Recently, two certificateless three-party authenticated key agreement protocols were proposed, and both protocols were claimed they can meet the desirable security properties including forward security, key compromise impersonation…
With the advances in 5G and IoT devices, the industries are vastly adopting artificial intelligence (AI) techniques for improving classification and prediction-based services. However, the use of AI also raises concerns regarding privacy…
As the financial industry becomes more interconnected and reliant on digital systems, fraud detection systems must evolve to meet growing threats. Cloud-enabled Transformer models present a transformative opportunity to address these…
Temporal Key Integrity Protocol (TKIP) is a provisional solution for Wired Equivalent Privacy (WEP) security loopholes present in already widely deployed legacy 802.11 wireless devices. In this work, we model and analyse the computational…
The prevalent use of Transformer-like models, exemplified by ChatGPT in modern language processing applications, underscores the critical need for enabling private inference essential for many cloud-based services reliant on such models.…
Multiparty session types are designed to abstractly capture the structure of communication protocols and verify behavioural properties. One important such property is progress, i.e., the absence of deadlock. Distributed algorithms often…
With the proliferation of various online and mobile payment systems, credit card fraud has emerged as a significant threat to financial security. This study focuses on innovative applications of the latest Transformer models for more robust…
In this work, we introduce an innovative autoregressive model leveraging Generative Pretrained Transformer (GPT) architectures, tailored for fraud detection in payment systems. Our approach innovatively confronts token explosion and…
It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g., fully homomorphic encryption (FHE), and multi-party computation (MPC), are popular…
In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data. We consider a variant of this problem, where the input data can be shared for machine learning training…
Device-independent quantum cryptography allows security even if the devices used to execute the protocol are untrusted - whether this is due to unknown imperfections in the implementation, or because the adversary himself constructed them…