Confidentiality-Preserving Collaborative Bayesian Networks

Effective large-scale process optimization in manufacturing industries requires close cooperation between different parties of human experts who encode their knowledge of related domains as Bayesian network models. For example, parties in the steel industry must collaboratively use their Bayesian networks on process parameters at the maker,...

Liveness checking of Streamlined Blockchain Consensus

Byzantine consensus protocols are designed to build resilient systems to achieve consensus under Byzantine settings, maintaining safety guarantees under any network synchrony model and providing liveness in partially or fully synchronous networks.<br/>However, several Byzantine consensus protocols have been shown to violate liveness properties...

Share your Secrets for Private Forecasting with Vertical Federated Learning

Vertical federated learning’s (VFL) immense potential for time series forecasting in industrial applications such as predictive maintenance and machine control remains untapped. Critical challenges to be addressed in the manufacturing industry include small and noisy datasets, model explainability, and stringent privacy requirements for training...

Tailoring Attacks To Federated Continual Learning Models

Federated learning enables training machine learning models on decentralized data sources without centrally aggregating sensitive information. Continual learning, on the other hand, focuses on learning and adapting to new tasks over time while avoiding the catastrophic forgetting of knowledge from previously encountered tasks. Federated...

Natural Language Processing and Tabular Data sets in Federated Continual Learning: A usability study of FCL in domains beyond Image classification

Federated Continual Learning (FCL) is a emerging field with strong roots in Image classification. However, limited research has been done on its potential in Natural Language Processing and Tabular datasets. With recent developments in A.I. with language models and the widespread use of mobile devices, it becomes relevant to consider FCL’s...

Training diffusion models with federated learning: A communication-efficient model for cross-silo federated image generation

The training of diffusion-based models for image generation is predominantly controlled by a select few Big Tech companies, raising concerns about privacy, copyright, and data authority due to the lack of transparency regarding training data. Hence, we propose a federated diffusion model scheme that enables the independent and collaborative...

Approximate Gradient Inversion Attack on Federated Learning

Federated learning is a private-by-design distributed learning paradigm where clients train local models on their own data before a central server aggregates their local updates to compute a global model. Depending on the aggregation method used, the local updates are either the gradients or the weights of local learning models. Unfortunately,...

Approaching Message Optimal Byzantine Reliable Broadcast using Routing

In this paper we will consider the Byzantine Reliable Broadcast problem on partially connected net- works. We introduce an routing algorithm for networks with a known topology. It will show that when this is combined with cryptographic signatures, we can use the routing algorithm to create an optimal amount of messages. We will introduce a few...

Byzantine-Resilient Real-Time Reliable Broadcast on Partially Connected Topology Cases

Increasing digitalisation of society due to technical advancement has increased the appearance and size of cyber- physical systems. These systems require real-time reliable control, which comes with its challenges. These systems need reliable communication despite the presence of attacks or faulty processes and bad connections, which can disrupt...

Decreasing message complexity in Byzantine Fault Tolerant communications using Consistent-Broadcast

During this research we have replaced Bracha’s layer in the state-of-the-art Bracha-Dolev protocol to improve the performance by decreasing the message complexity of the protocol running on top of a given network topology so long as the requirements stated by Bracha and Dolev are met. Bracha-Dolev is an algorithm that is used to establish a...

Optimizing trust in networks through exchange of message paths

Distributed systems are networks of nodes depending on each other. However, each network can have multiple faulty nodes, which are either malfunctioning or malicious. Bracha's algorithm allows correct nodes inside the network to agree on certain information, while tolerating a certain amount of faulty nodes. Nodes exchange Send, Echo and Ready...

Discovering the Topology in an Unknown Network

Discovering the topology in an unknown network is a fundamental problem for the distributed systems that faces several backlashes due to the proneness of such systems to Byzantine (i.e. arbitrary or malicious) failures. During the past decades, several protocols were developed to allow a network to be resilient up to a certain number of...

Energy Consumption and Scalability of Transmitting Firmware Updates Over LoRa

The rapid growth of LoRa sensor networks lead to more and more maintenence challenges. One of them is wirelessly updating the firmware, especially for the ones that are hard or dangerous to reach. Is it feasible to do a firmware update over LoRa, and what is its additional power consumption of the wireless sensors? In this thesis a LoRa Class B...

Message efficient Byzantine Reliable Broadcast protocols on known topologies

In this paper, we consider the Reliable Communication and Byzantine Reliable Broadcast problems on partially connected networks with authenticated links. We consider the Reliable Communication (RC) problem on partially connected networks, and the Byzantine Reliable Broadcast (BRB) problem on partially and fully connected networks. Danny Dolev's...

Byzantine Reliable Broadcast on partially connected networks with signatures

In this paper, we consider Byzantine reliable broadcast on partially connected networks using signatures. Byzantine reliable broadcast in partially connected and authenticated networks can be achieved by combining two algorithms, Gabriel Bracha's double-echo broadcast protocol and Danny Dolev's reliable communication protocol. Bracha's algorithm...

Trusted Execution Environments in Byzantine-Tolerant Networks

Achieving consensus in a network is one of the most important performance bottlenecks in distributed computing. This paper takes a look at the existing protocols for achieving Byzantine Reliable Broadcast on asynchronous partially connected networks and how these protocols change to leverage the fact that some nodes have access to Trusted...

Broadcasting protocol: Applying Optimizations from Bracha-Dolev Broadcast Protocol to Bracha-CPABroadcast Protocol

Broadcast protocols are a crucial building block for some Agreement protocols. These are protocols used to reach an agreement on common values, action or datum in a distributed system through sending it in a message for other processes to accept it \cite{bracha1987asynchronous}. Byzantine processes are processes that hinder the network from...