Topology-aware differential privacy for decentralized image classification
Image classification is a fundamental artificial intelligence task that labels images into one of
some predefined classes. However, training complex image classification models requires a …
some predefined classes. However, training complex image classification models requires a …
Privacy-Preserving Distributed Optimization and Learning
Distributed optimization and learning has recently garnered great attention due to its wide
applications in sensor networks, smart grids, machine learning, and so forth. Despite rapid …
applications in sensor networks, smart grids, machine learning, and so forth. Despite rapid …
Distributed dynamic online learning with differential privacy via path-length measurement
Dynamic online learning has been given great concerns as real-time and non-stationary
systems develop and it can be used for solving many practical sequential decision problems …
systems develop and it can be used for solving many practical sequential decision problems …
Graph-homomorphic perturbations for private decentralized learning
Decentralized algorithms for stochastic optimization and learning rely on the diffusion of
information through repeated local exchanges of intermediate estimates. Such structures are …
information through repeated local exchanges of intermediate estimates. Such structures are …
Communication and security issues in online learning during the COVID-19 Pandemic
C Metallidou, KE Psannis, S Goudos… - 2021 IEEE 9th …, 2021 - ieeexplore.ieee.org
This era is characterized by the rapid evolution of technology and its application in all
sectors of day to day life. At the same time, the outbreak of the COVID-19 pandemic has …
sectors of day to day life. At the same time, the outbreak of the COVID-19 pandemic has …
Evaluating Port Emissions Prediction Model Resilience Against Cyberthreats
VSS Vennam, CD Paternina-Arboleda… - International Conference …, 2024 - Springer
The port sector is evolving, influencing areas such as operations, infrastructure, governance,
technology, partnerships, and commercial strategies. AI can significantly improve the …
technology, partnerships, and commercial strategies. AI can significantly improve the …
Distributed Quantized Algorithms in Adversarial Networks
We propose a distributed gradient algorithm to solve an optimization problem over a
multiagent network in which a fraction of the nodes are malicious. We assume the …
multiagent network in which a fraction of the nodes are malicious. We assume the …