Related papers: Synchronous Hybrid Message-Adversary
The reliability of a learning model is key to the successful deployment of machine learning in various applications. However, it is difficult to describe the phenomenon due to the complicated nature of the problems in machine learning. It…
The widespread adoption of large-scale machine learning models in recent years highlights the need for distributed computing for efficiency and scalability. This work introduces a novel distributed machine learning paradigm --…
Many problems of interest for cyber-physical network systems can be formulated as Mixed-Integer Linear Programs in which the constraints are distributed among the agents. In this paper we propose a distributed algorithmic framework to solve…
In this work we look at Byzantine consensus in asynchronous systems under the local broadcast model. In the local broadcast model, a message sent by any node is received identically by all of its neighbors in the communication network,…
Generative adversarial networks (GANs) are a novel approach to generative modelling, a task whose goal it is to learn a distribution of real data points. They have often proved difficult to train: GANs are unlike many techniques in machine…
Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles. However, despite their superior…
Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that…
Implementations of SGD on distributed systems create new vulnerabilities, which can be identified and misused by one or more adversarial agents. Recently, it has been shown that well-known Byzantine-resilient gradient aggregation schemes…
Standard federated learning algorithms are vulnerable to adversarial nodes, a.k.a. Byzantine failures. To solve this issue, robust distributed learning algorithms have been developed, which typically replace parameter averaging by robust…
Federated learning (FL) is a distributed machine learning paradigm that enables training models on decentralized data. The field of FL security against poisoning attacks is plagued with confusion due to the proliferation of research that…
Over the past four decades, distributed security has undergone a remarkable transformation -- from crash-fault tolerant protocols designed for controlled environments to sophisticated Byzantine-resilient architectures operating in open,…
Modern supply networks are complex interconnected systems. Multi-agent models are increasingly explored to optimise their performance. Most research assumes agents will have full observability of the system by having a single policy…
We begin with a disquieting paradox: human machine teaming (HMT) often produces results worse than either the human or machine would produce alone. Critically, this failure is not a result of inferior human modeling or a suboptimal…
We propose Teamwork Synthesis, a version of the distributed synthesis problem with application to teamwork multi-agent systems. We reformulate the distributed synthesis question by dropping the fixed interaction architecture among agents as…
Modern society is dependent on distributed software systems and to verify them different modelling languages such as mobile ambients were developed. To analyse the quality of mobile ambients as a good foundational model for distributed…
Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, but its robustness is threatened by Byzantine behaviors such as data and model poisoning. Existing defenses face fundamental…
In stochastic modeling, the excess entropy -- the mutual information shared between a process's past and future -- represents the fundamental lower bound of the memory needed to simulate its dynamics. However, this bound cannot be saturated…
Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Such model-based methods utilize mathematical formulations that represent the underlying physics, prior information and…
Metastable failure is a recent abstraction of a pattern of failures that occurs frequently in real-world distributed storage systems. In this paper, we propose a formal analysis and modeling of metastable failures in replicated storage…
This paper proposed a distributed filter for spatially interconnected systems (SISs), which considers missing measurements in the sensors of sub-systems. An SIS is established by many similar sub-systems that directly interact or…