Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Byun, Junyoung"'
Programmatically generated synthetic data has been used in differential private training for classification to enhance performance without privacy leakage. However, as the synthetic data is generated from a random process, the distribution of real da
Externí odkaz:
http://arxiv.org/abs/2412.09842
Deep neural networks are widely known to be susceptible to adversarial examples, which can cause incorrect predictions through subtle input modifications. These adversarial examples tend to be transferable between models, but targeted attacks still h
Externí odkaz:
http://arxiv.org/abs/2305.14846
Publikováno v:
Pattern Recognition, January 2025, Volume 157, 110890
This study aims to alleviate the trade-off between utility and privacy of differentially private clustering. Existing works focus on simple methods, which show poor performance for non-convex clusters. To fit complex cluster distributions, we propose
Externí odkaz:
http://arxiv.org/abs/2304.13886
Publikováno v:
In Expert Systems With Applications 5 December 2024 256
Publikováno v:
In Pattern Recognition January 2025 157
The transferability of adversarial examples allows the deception on black-box models, and transfer-based targeted attacks have attracted a lot of interest due to their practical applicability. To maximize the transfer success rate, adversarial exampl
Externí odkaz:
http://arxiv.org/abs/2203.09123
CNN-based face recognition models have brought remarkable performance improvement, but they are vulnerable to adversarial perturbations. Recent studies have shown that adversaries can fool the models even if they can only access the models' hard-labe
Externí odkaz:
http://arxiv.org/abs/2111.04371
While deep neural networks show unprecedented performance in various tasks, the vulnerability to adversarial examples hinders their deployment in safety-critical systems. Many studies have shown that attacks are also possible even in a black-box sett
Externí odkaz:
http://arxiv.org/abs/2101.04829
Publikováno v:
IEEE Intelligent Systems, 2022
Federated learning is a paradigm that enables local devices to jointly train a server model while keeping the data decentralized and private. In federated learning, since local data are collected by clients, it is hardly guaranteed that the data are
Externí odkaz:
http://arxiv.org/abs/2012.01700
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.