Zobrazeno 1 - 10
of 135
pro vyhledávání: '"Laoutaris, Nikolaos P."'
Autor:
Chu, Tianyue, Laoutaris, Nikolaos
Federated Learning (FL) permits different parties to collaboratively train a global model without disclosing their respective local labels. A crucial step of FL, that of aggregating local models to produce the global one, shares many similarities wit
Externí odkaz:
http://arxiv.org/abs/2401.01168
We present a novel technique for modulating the appearance frequency of a few tokens within a dataset for encoding an invisible watermark that can be used to protect ownership rights upon data. We develop optimal as well as fast heuristic algorithms
Externí odkaz:
http://arxiv.org/abs/2312.16547
In this paper, we propose Puppy, the first formally defined framework for converting any symmetric watermarking into a publicly verifiable one. Puppy allows anyone to verify a watermark any number of times with the help of an untrusted third party, w
Externí odkaz:
http://arxiv.org/abs/2312.09125
Federated learning (FL) is a paradigm that allows several client devices and a server to collaboratively train a global model, by exchanging only model updates, without the devices sharing their local training data. These devices are often constraine
Externí odkaz:
http://arxiv.org/abs/2310.19958
Autor:
Salamanos, Nikos, Leonidou, Pantelitsa, Laoutaris, Nikolaos, Sirivianos, Michael, Aspri, Maria, Paraschiv, Marius
In light of the growing impact of disinformation on social, economic, and political landscapes, accurate and efficient identification methods are increasingly critical. This paper introduces HyperGraphDis, a novel approach for detecting disinformatio
Externí odkaz:
http://arxiv.org/abs/2310.01113
Autor:
Wang, Rui, Wang, Xingkai, Chen, Huanhuan, Decouchant, Jérémie, Picek, Stjepan, Laoutaris, Nikolaos, Liang, Kaitai
Byzantine-robust Federated Learning (FL) aims to counter malicious clients and train an accurate global model while maintaining an extremely low attack success rate. Most existing systems, however, are only robust when most of the clients are honest.
Externí odkaz:
http://arxiv.org/abs/2208.10161
Autor:
Chu, Tianyue, Garcia-Recuero, Alvaro, Iordanou, Costas, Smaragdakis, Georgios, Laoutaris, Nikolaos
Publikováno v:
Network and Distributed System Security (NDSS) Symposium 2023
We present a Federated Learning (FL) based solution for building a distributed classifier capable of detecting URLs containing GDPR-sensitive content related to categories such as health, sexual preference, political beliefs, etc. Although such a cla
Externí odkaz:
http://arxiv.org/abs/2201.13086
"Data" is becoming an indispensable production factor, just like land, infrastructure, labor or capital. As part of this, a myriad of applications in different sectors require huge amounts of information to feed models and algorithms responsible for
Externí odkaz:
http://arxiv.org/abs/2201.04561
A large number of Data Marketplaces (DMs) have appeared in the last few years to help owners monetise their data, and data buyers fuel their marketing process, train their ML models, and perform other data-driven decision processes. In this paper, we
Externí odkaz:
http://arxiv.org/abs/2111.04427
Autor:
Paraschiv, Marius, Salamanos, Nikos, Iordanou, Costas, Laoutaris, Nikolaos, Sirivianos, Michael
As recent events have demonstrated, disinformation spread through social networks can have dire political, economic and social consequences. Detecting disinformation must inevitably rely on the structure of the network, on users particularities and o
Externí odkaz:
http://arxiv.org/abs/2109.11781