相关论文: Verifiable Split Learning via zk-SNARKs

Split learning (SL) enables data privacy preservation by allowing clients to collaboratively train a deep learning model with the server without sharing raw data. However, SL still has limitations such as potential data privacy leakage and…

Split learning (SL) is a new collaborative learning technique that allows participants, e.g. a client and a server, to train machine learning models without the client sharing raw data. In this setting, the client initially applies its part…

Deep neural networks (DNNs) are prominent due to their superior performance in many fields. The deep-learning-as-a-service (DLaaS) paradigm enables individuals and organizations (clients) to outsource their DNN learning tasks to the…

Machine learning is increasingly deployed through outsourced and cloud-based pipelines, which improve accessibility but also raise concerns about computational integrity, data privacy, and model confidentiality. Zero-knowledge proofs (ZKPs)…

A non-interactive ZK (NIZK) proof enables verification of NP statements without revealing secrets about them. However, an adversary that obtains a NIZK proof may be able to clone this proof and distribute arbitrarily many copies of it to…

Blockchain-based federated learning has gained significant interest over the last few years with the increasing concern for data privacy, advances in machine learning, and blockchain innovation. However, gaps in security and scalability…

In recent years, there have been great advances in the field of decentralized learning with private data. Federated learning (FL) and split learning (SL) are two spearheads possessing their pros and cons, and are suited for many user…

Many service systems rely on verifiable identity-related information of their users. Manipulation and unwanted exposure of this privacy-relevant information, however, must at the same time be prevented and avoided. Peer-to-peer…

Federated learning (FL) enables multiple participants to collaboratively train machine learning models while ensuring their data remains private and secure. Blockchain technology further enhances FL by providing stronger security, a…

Zero-knowledge proofs (ZKPs) have evolved from being a theoretical concept providing privacy and verifiability to having practical, real-world implementations, with SNARKs (Succinct Non-Interactive Argument of Knowledge) emerging as one of…

We introduce PyVertical, a framework supporting vertical federated learning using split neural networks. The proposed framework allows a data scientist to train neural networks on data features vertically partitioned across multiple owners…

Formal verification provides critical security assurances for neural networks, yet its practical application suffers from the long verification time. This work introduces a novel method for training verification-friendly neural networks,…

Non-Interactive Zero Knowledge (NIZK) proofs, such as zkSNARKS, let one prove knowledge of private data without revealing it or interacting with a verifier. While existing tooling focuses on specifying the predicate to be proven, real-world…

Collaborative machine learning in sensitive domains demands scalable, privacy preserving solutions for enterprise deployment. Conventional Federated Learning (FL) relies on a central server, introducing single points of failure and privacy…

Learning from data owned by several parties, as in federated learning, raises challenges regarding the privacy guarantees provided to participants and the correctness of the computation in the presence of malicious parties. We tackle these…

To use neural networks in safety-critical settings it is paramount to provide assurances on their runtime operation. Recent work on ReLU networks has sought to verify whether inputs belonging to a bounded box can ever yield some undesirable…

Split learning (SL) is an emergent distributed learning framework which can mitigate the computation and wireless communication overhead of federated learning. It splits a machine learning model into a device-side model and a server-side…

In the evolution towards 6G, integrating Artificial Intelligence (AI) with advanced network infrastructure emerges as a pivotal strategy for enhancing network intelligence and resource utilization. Existing distributed learning frameworks…

Machine unlearning aims to remove points from the training dataset of a machine learning model after training: e.g., when a user requests their data to be deleted. While many unlearning methods have been proposed, none of them enable users…

This article aims to study intrusion attacks and then develop a novel cyberattack detection framework to detect cyberattacks at the network layer (e.g., Brute Password and Flooding of Transactions) of blockchain networks. Specifically, we…