Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Alejandro E. Brito"'
Autor:
Daniel M Bittner, Alejandro E Brito, Mohsen Ghassemi, Shantanu Rane, Anand D Sarwate, Rebecca N Wright
Publikováno v:
The Journal of Privacy and Confidentiality, Vol 10, Iss 2 (2020)
We consider privacy-preserving learning in the context of online learning. Insettings where data instances arrive sequentially in streaming fashion, incremental trainingalgorithms such as stochastic gradient descent (SGD) can be used to learn and upd
Externí odkaz:
https://doaj.org/article/8ed838b64a1340a6b69cb186bc6ce0db
Publikováno v:
SECURITY AND PRIVACY.
Autor:
Zikui Cai, Shantanu Rane, Alejandro E. Brito, Chengyu Song, Srikanth V. Krishnamurthy, Amit K. Roy-Chowdhury, M. Salman Asif
Adversarial attacks perturb images such that a deep neural network produces incorrect classification results. A promising approach to defend against adversarial attacks on natural multi-object scenes is to impose a context-consistency check, wherein,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::14d676bf8fcbb633ed7c3cec3c8dda25
http://arxiv.org/abs/2203.15230
http://arxiv.org/abs/2203.15230
Publikováno v:
SECRYPT
Autor:
Mohsen Ghassemi, Daniel M. Bittner, Rebecca N. Wright, Shantanu Rane, Alejandro E. Brito, Anand D. Sarwate
Publikováno v:
The Journal of Privacy and Confidentiality, Vol 10, Iss 2 (2020)
We consider privacy-preserving learning in the context of online learning. Insettings where data instances arrive sequentially in streaming fashion, incremental trainingalgorithms such as stochastic gradient descent (SGD) can be used to learn and upd
Autor:
Shantanu Rane, Alejandro E. Brito
Publikováno v:
WIFS
We analyze pool-based active learning under a differential privacy guarantee. At every active learning step, some samples are selected to be labeled by an oracle, and the new labels are used to update the classifier. We want to preserve differential
Publikováno v:
Journal of Proteomics. 129:71-77
Human experts can annotate peaks in MALDI-TOF profiles of detached N-glycans with some degree of accuracy. Even though MALDI-TOF profiles give only intact masses without any fragmentation information, expert knowledge of the most common glycans and b
Publikováno v:
CODASPY
We consider the problem of privacy-preserving data aggregation in a star network topology, i.e., several untrusting participants connected to a single aggregator. We require that the participants do not discover each other's data, and the service pro
Publikováno v:
Molecular & Cellular Proteomics. 12:996-1004
For over 30 years, protocols based on the mass spectrometry (MS) of permethylated derivatives, complemented by enzymatic degradations, have underpinned glycomic experiments aimed at defining the structures of individual glycans present in the complex
Publikováno v:
WIFS
We consider the challenge of performing efficient, fault-tolerant, privacy-preserving aggregate computations in a star topology, i.e., a massive number of participants connected to a single untrusted aggregator. The privacy constraints are that the p