Zobrazeno 1 - 10
of 3 915
pro vyhledávání: '"Lecuyer, A."'
Deep learning time-series models are often used to make forecasts that inform downstream decisions. Since these decisions can differ from those in the training set, there is an implicit requirement that time-series models will generalize outside of t
Externí odkaz:
http://arxiv.org/abs/2411.00126
We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our test-time adaptive models against adversarial examples. ARS extends the analysis of randomized smoothing using $f$-Differential Privacy to certify the adaptive compositi
Externí odkaz:
http://arxiv.org/abs/2406.10427
Autor:
Tholoniat, Pierre, Kostopoulou, Kelly, McNeely, Peter, Sodhi, Prabhpreet Singh, Varanasi, Anirudh, Case, Benjamin, Cidon, Asaf, Geambasu, Roxana, Lécuyer, Mathias
Publikováno v:
In ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP '24), November 4-6, 2024, Austin, TX, USA. ACM, New York, NY, USA, 27 pages
With the impending removal of third-party cookies from major browsers and the introduction of new privacy-preserving advertising APIs, the research community has a timely opportunity to assist industry in qualitatively improving the Web's privacy. Th
Externí odkaz:
http://arxiv.org/abs/2405.16719
We study Thompson Sampling-based algorithms for stochastic bandits with bounded rewards. As the existing problem-dependent regret bound for Thompson Sampling with Gaussian priors [Agrawal and Goyal, 2017] is vacuous when $T \le 288 e^{64}$, we derive
Externí odkaz:
http://arxiv.org/abs/2405.01010
Autor:
Kazmi, Mishaal, Lautraite, Hadrien, Akbari, Alireza, Tang, Qiaoyue, Soroco, Mauricio, Wang, Tao, Gambs, Sébastien, Lécuyer, Mathias
We present PANORAMIA, a privacy leakage measurement framework for machine learning models that relies on membership inference attacks using generated data as non-members. By relying on generated non-member data, PANORAMIA eliminates the common depend
Externí odkaz:
http://arxiv.org/abs/2402.09477
The Adam optimizer is a popular choice in contemporary deep learning, due to its strong empirical performance. However we observe that in privacy sensitive scenarios, the traditional use of Differential Privacy (DP) with the Adam optimizer leads to s
Externí odkaz:
http://arxiv.org/abs/2312.14334
The widespread adoption of encryption in network protocols has significantly improved the overall security of many Internet applications. However, these protocols cannot prevent network side-channel leaks -- leaks of sensitive information through the
Externí odkaz:
http://arxiv.org/abs/2310.06293
Autor:
Tom Hillary, Liesbeth F. E. Ghys, Fabienne Willaert, Sandra Swimberghe, Myriam Lecuyer, Pierre‐Dominique Ghislain, Joachim Morrens, Jo Lambert
Publikováno v:
JEADV Clinical Practice, Vol 3, Iss 5, Pp 1487-1498 (2024)
Abstract Background In the Belgian DISCOVER study, conducted in 2011–2012 before the advent of the IL‐17 and IL‐23 Inhibitors, significant undertreatment of patients with plaque psoriasis was reported. Objectives The present study aimed to re
Externí odkaz:
https://doaj.org/article/f56fafeb56e74bccbd38fdb398c80379
Publikováno v:
Journal of Consumer Marketing, 2024, Vol. 41, Issue 6, pp. 648-657.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/JCM-04-2022-5299
Differentially-private (DP) databases allow for privacy-preserving analytics over sensitive datasets or data streams. In these systems, user privacy is a limited resource that must be conserved with each query. We propose Turbo, a novel, state-of-the
Externí odkaz:
http://arxiv.org/abs/2306.16163