Zobrazeno 1 - 10
of 20
pro vyhledávání: '"ERSOY, Oğuzhan"'
Decentralized machine learning (DL) has been receiving an increasing interest recently due to the elimination of a single point of failure, present in Federated learning setting. Yet, it is threatened by the looming threat of Byzantine clients who in
Externí odkaz:
http://arxiv.org/abs/2404.17970
Split learning is a collaborative learning design that allows several participants (clients) to train a shared model while keeping their datasets private. Recent studies demonstrate that collaborative learning models, specifically federated learning,
Externí odkaz:
http://arxiv.org/abs/2302.09578
Publikováno v:
NDSS Symposium 2024
Deep neural networks (DNNs) have demonstrated remarkable performance across various tasks, including image and speech recognition. However, maximizing the effectiveness of DNNs requires meticulous optimization of numerous hyperparameters and network
Externí odkaz:
http://arxiv.org/abs/2302.06279
Deep learning models achieve excellent performance in numerous machine learning tasks. Yet, they suffer from security-related issues such as adversarial examples and poisoning (backdoor) attacks. A deep learning model may be poisoned by training with
Externí odkaz:
http://arxiv.org/abs/2302.00747
Payment channel networks (PCNs) enhance the scalability of blockchains by allowing parties to conduct transactions off-chain, i.e, without broadcasting every transaction to all blockchain participants. To conduct transactions, a sender and a receiver
Externí odkaz:
http://arxiv.org/abs/2207.11615
Autor:
Abad, Gorka, Paguada, Servio, Ersoy, Oguzhan, Picek, Stjepan, Ramírez-Durán, Víctor Julio, Urbieta, Aitor
Federated Learning (FL) enables collaborative training of Deep Learning (DL) models where the data is retained locally. Like DL, FL has severe security weaknesses that the attackers can exploit, e.g., model inversion and backdoor attacks. Model inver
Externí odkaz:
http://arxiv.org/abs/2203.08689
Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. Building a powerful GNN model is not a trivial task, as it requires a large amount of training data, powerful computing resources, and human expertis
Externí odkaz:
http://arxiv.org/abs/2110.11024
Payment channel networks like Bitcoin's Lightning network are an auspicious approach for realizing high transaction throughput and almost-instant confirmations in blockchain networks. However, the ability to successfully make payments in such network
Externí odkaz:
http://arxiv.org/abs/1911.08803
Existing permissionless blockchain solutions rely on peer-to-peer propagation mechanisms, where nodes in a network transfer transaction they received to their neighbors. Unfortunately, there is no explicit incentive for such transaction propagation.
Externí odkaz:
http://arxiv.org/abs/1712.07564
A recent work of Harn and Fuyou presents the first multilevel (disjunctive) threshold secret sharing scheme based on the Chinese Remainder Theorem. In this work, we first show that the proposed method is not secure and also fails to work with a certa
Externí odkaz:
http://arxiv.org/abs/1605.07988