Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Marson, Giorgia Azzurra"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence, 38(19), 2024, 21859-21868
Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to efficiently estab
Externí odkaz:
http://arxiv.org/abs/2312.10132
Secure Aggregation (SA) is a key component of privacy-friendly federated learning applications, where the server learns the sum of many user-supplied gradients, while individual gradients are kept private. State-of-the-art SA protocols protect indivi
Externí odkaz:
http://arxiv.org/abs/2308.02208
The wide success of Bitcoin has led to a huge surge of alternative cryptocurrencies (altcoins). Most altcoins essentially fork Bitcoin's code with minor modifications, such as the number of coins to be minted, the block size, and the block generation
Externí odkaz:
http://arxiv.org/abs/2205.07478
Autor:
Marson, Giorgia Azzurra, Andreina, Sebastien, Alluminio, Lorenzo, Munichev, Konstantin, Karame, Ghassan
Scalability remains one of the biggest challenges to the adoption of permissioned blockchain technologies for large-scale deployments. Permissioned blockchains typically exhibit low latencies, compared to permissionless deployments -- however at the
Externí odkaz:
http://arxiv.org/abs/2109.10302
Modern blockchains support a variety of distributed applications beyond cryptocurrencies, including smart contracts -- which let users execute arbitrary code in a distributed and decentralized fashion. Regardless of their intended application, blockc
Externí odkaz:
http://arxiv.org/abs/2101.05543
Recent studies have shown that federated learning (FL) is vulnerable to poisoning attacks that inject a backdoor into the global model. These attacks are effective even when performed by a single client, and undetectable by most existing defensive te
Externí odkaz:
http://arxiv.org/abs/2011.02167
Autor:
Marson, Giorgia Azzurra
A secure channel is a cryptographic protocol that adds security to unprotected network connections. Prominent examples include the Transport Layer Security (TLS) and the Secure Shell (SSH) protocols. Because of their large-scale deployment, these pro
Externí odkaz:
http://tuprints.ulb.tu-darmstadt.de/6021/1/main.pdf
Deep Learning has been shown to be particularly vulnerable to adversarial samples. To combat adversarial strategies, numerous defensive techniques have been proposed. Among these, a promising approach is to use randomness in order to make the classif
Externí odkaz:
http://arxiv.org/abs/1812.04293
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.