Zobrazeno 1 - 10
of 21 782
pro vyhledávání: '"Leith, A."'
Data forging attacks provide counterfactual proof that a model was trained on a given dataset, when in fact, it was trained on another. These attacks work by forging (replacing) mini-batches with ones containing distinct training examples that produc
Externí odkaz:
http://arxiv.org/abs/2411.05658
Autor:
Gusain, Vaibhav, Leith, Douglas
Publikováno v:
LNCS,volume 13981, 2023, 423-429
In this paper we propose use of a k-anonymity-like approach for evaluating the privacy of redacted text. Given a piece of redacted text we use a state of the art transformer-based deep learning network to reconstruct the original text. This generates
Externí odkaz:
http://arxiv.org/abs/2410.07772
Autor:
Abdisatarov, B., Bafia, D., Murthy, A., Eremeev, G., Elsayed-Ali, H. E., Lee, J., Netepenko, A., Carlos, C. P. A., Leith, S., Rosaz, G. J., Romanenko, A., Grassellino, A.
Niobium films are a key component in modern two-dimensional superconducting qubits, yet their contribution to the total qubit decay rate is not fully understood. The presence of different layers of materials and interfaces makes it difficult to ident
Externí odkaz:
http://arxiv.org/abs/2407.08856
Autor:
Bianchi, Antonio, Bonura, Marco, Carlos, Carlota P. A., Leith, Stewart, Rosaz, Guillaume, Senatore, Carmine, Delsolaro, Walter Venturini
Niobium-coated copper radio-frequency cavities are cost-effective alternatives to bulk niobium cavities, given the lower material costs of copper substrates and their operation in liquid helium at around 4.2 K. However, these cavities historically ex
Externí odkaz:
http://arxiv.org/abs/2403.11245
Autor:
Shams, Sulthana, Leith, Douglas
This paper proposes a novel method for detecting shilling attacks in Matrix Factorization (MF)-based Recommender Systems (RS), in which attackers use false user-item feedback to promote a specific item. Unlike existing methods that use either use sup
Externí odkaz:
http://arxiv.org/abs/2312.00512
Non-Alcoholic Steatohepatitis Patient Characterization and Real-World Management Approaches in Italy
Publikováno v:
Pragmatic and Observational Research, Vol Volume 15, Pp 185-200 (2024)
Elisabetta Bugianesi,1 Luca Miele,2,3 Giovanna Donnarumma,4 Katrine Grau,5 Mariarosaria Mancuso,4 Preethy Prasad,5 Andrea Leith,6 Victoria Higgins6 1Division of Gastroenterology, Department of Medical Sciences, University of Torino, AOU Città della
Externí odkaz:
https://doaj.org/article/10797412f5f44467b03a99197f6a259b
Autor:
Young, David, Leith, Douglas
Publikováno v:
30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Proceedings (2022) 423 - 428
We develop a novel latent-bandit algorithm for tackling the cold-start problem for new users joining a recommender system. This new algorithm significantly outperforms the state of the art, simultaneously achieving both higher accuracy and lower regr
Externí odkaz:
http://arxiv.org/abs/2305.18305
The performance of superconducting radio-frequency (SRF) cavities is sometimes limited by local defects. To investigate the RF properties of these local defects, especially those that nucleate RF magnetic vortices, a near-field magnetic microwave mic
Externí odkaz:
http://arxiv.org/abs/2305.07746
Autor:
Shams, Sulthana, Leith, Douglas
In practice, users of a Recommender System (RS) fall into a few clusters based on their preferences. In this work, we conduct a systematic study on user-cluster targeted data poisoning attacks on Matrix Factorisation (MF) based RS, where an adversary
Externí odkaz:
http://arxiv.org/abs/2305.04694
Autor:
Thembeka K. Mtetwa, Edward P. Snelling, Peter E. Buss, Ashleigh C. Donaldson, Annette Roug, Leith C. R. Meyer
Publikováno v:
BMC Veterinary Research, Vol 20, Iss 1, Pp 1-13 (2024)
Abstract Background Monitoring blood oxygenation is essential in immobilised rhinoceros, which are susceptible to opioid-induced hypoxaemia. This study assessed the reliability, clinical performance and trending ability of the Nonin PalmSAT 2500 A pu
Externí odkaz:
https://doaj.org/article/4eb12c81183a4f839da9abde99572767