Zobrazeno 1 - 10
of 1 420
pro vyhledávání: '"Calzavara, P."'
We present Timber, the first white-box poisoning attack targeting decision trees. Timber is based on a greedy attack strategy leveraging sub-tree retraining to efficiently estimate the damage performed by poisoning a given training instance. The atta
Externí odkaz:
http://arxiv.org/abs/2410.00862
Image datasets serve as the foundation for machine learning models in computer vision, significantly influencing model capabilities, performance, and biases alongside architectural considerations. Therefore, understanding the composition and distribu
Externí odkaz:
http://arxiv.org/abs/2408.04072
Verifiable learning advocates for training machine learning models amenable to efficient security verification. Prior research demonstrated that specific classes of decision tree ensembles -- called large-spread ensembles -- allow for robustness veri
Externí odkaz:
http://arxiv.org/abs/2402.14988
Verifying the robustness of machine learning models against evasion attacks at test time is an important research problem. Unfortunately, prior work established that this problem is NP-hard for decision tree ensembles, hence bound to be intractable f
Externí odkaz:
http://arxiv.org/abs/2305.03626
Autor:
Wolfgang G. Philipp-Dormston, Lasse R. Braathen, Colin A. Morton, Merete Haedersdal, Yolanda Gilaberte, Nicole Basset-Seguin, Elena Sotiriou, Stine Regin Wiegell, Piergiacomo Calzavara-Pinton, Thomas Dirschka, Hans Christian Wulf, Günther Hofbauer, Rolf Markus Szeimies
Publikováno v:
Acta Dermato-Venereologica, Vol 104 (2024)
Keratinocyte-derived skin cancers comprise basal cell carcinoma, squamous cell carcinoma, its precursor actinic keratosis, and Bowen’s disease. Historically, this group of neoplasms has been subsumed under the term non-melanoma skin cancer. However
Externí odkaz:
https://doaj.org/article/2c0b6efff2fc42ef8929fbe1709bc61b
Autor:
Calzavara, Martino, Kuriatnikov, Yevhenii, Deutschmann-Olek, Andreas, Motzoi, Felix, Erne, Sebastian, Kugi, Andreas, Calarco, Tommaso, Schmiedmayer, Jörg, Prüfer, Maximilian
We present our new experimental and theoretical framework which combines a broadband superluminescent diode (SLED/SLD) with fast learning algorithms to provide speed and accuracy improvements for the optimization of 1D optical dipole potentials, here
Externí odkaz:
http://arxiv.org/abs/2210.07776
We present a new approach to the global fairness verification of tree-based classifiers. Given a tree-based classifier and a set of sensitive features potentially leading to discrimination, our analysis synthesizes sufficient conditions for fairness,
Externí odkaz:
http://arxiv.org/abs/2209.13179
Autor:
Deutschmann-Olek, Andreas, Tajik, Mohammadamin, Calzavara, Martino, Schmiedmayer, Jörg, Calarco, Tommaso, Kugi, Andreas
Publikováno v:
2022 IEEE 61st Conference on Decision and Control (CDC)
The ability to manipulate clouds of ultra-cold atoms is crucial for modern experiments on quantum manybody systems and quantum thermodynamics as well as future metrological applications of Bose-Einstein condensate. While optical manipulation offers a
Externí odkaz:
http://arxiv.org/abs/2208.00706
Autor:
Camila Pereira Santos, Jerlane Tarcila Gomes Teles, Georgia Freitas Guimaraes, Laura Helena Vega Gonzales Gil, Amanda Mota Vieira, Jose Wilton Pinheiro Junior, Carlos Eduardo Calzavara-Silva, Rita de Cassia Carvalho Maia
Publikováno v:
Open Veterinary Journal, Vol 14, Iss 4, Pp 1019-1028 (2024)
Background: Canine distemper is a worldwide spread disease that has been described in 12 families of mammals, especially in the Carnivora order, being better studied in domestic canines where vaccination represents the best means of control. Canine d
Externí odkaz:
https://doaj.org/article/d8e0f675acbc496cafb60832675755cc
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.