Results 11 to 20 of about 4,006,758 (366)
Pretrained Transformers Improve Out-of-Distribution Robustness [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 Although pretrained Transformers such as BERT achieve high accuracy on in-distribution examples, do they generalize to new distributions? We systematically measure out-of-distribution (OOD) generalization for seven NLP datasets by constructing a new ...
Dan Hendrycks +5 more
semanticscholar +1 more source
BMC Medical Informatics and Decision Making, 2022 Background Analysing distributed medical data is challenging because of data sensitivity and various regulations to access and combine data. Some privacy-preserving methods are known for analyzing horizontally-partitioned data, where different ...
Bart Kamphorst +4 more
doaj +1 more source
Towards Evaluating the Robustness of Neural Networks [PDF]
IEEE Symposium on Security and Privacy, 2016 Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input x and any target classification t, it is possible to find a new input x' that is ...
Nicholas Carlini, D. Wagner
semanticscholar +1 more source
A robust robust optimization result [PDF]
Operations Research Letters, 2012 We study the loss in objective value when an inaccurate objective is optimized instead of the true one, and show that "on average" this loss is very small, for an arbitrary compact feasible region.
Martina Gancarova, Michael J. Todd
openaire +3 more sources
Journal of Cryptology, 2010 We provide a provable-security treatment of "robust" encryption. Robustness means it is hard to produce a ciphertext that is valid for two different users. Robustness makes explicit a property that has been implicitly assumed in the past. We argue that it is an essential conjunct of anonymous encryption.
Abdalla, Michel +2 more
openaire +7 more sources
Fish mislabelling in France: substitution rates and retail types [PDF]
PeerJ, 2015 Market policies have profound implications for consumers as well as for the management of resources. One of the major concerns in fish trading is species mislabelling: the commercial name used does not correspond to the product, most often because the ...
Julien Bénard-Capelle +5 more
doaj +2 more sources
Privacy and Robustness in Federated Learning: Attacks and Defenses [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2020 As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges.
L. Lyu +6 more
semanticscholar +1 more source
SSRN Electronic Journal, 2011 We compute the breakdown point of the subsampling quantile of a general statistic, and show that it is increasing in the subsampling block size and the breakdown point of the statistic. These results imply fragile subsampling quantiles for moderate block sizes, also when subsampling procedures are applied to robust statistics.
Camponovo, Lorenzo +2 more
openaire +6 more sources
Robustness of entanglement [PDF]
Physical Review A, 1999 27 pages, LaTex, 3 ...
Vidal, Guifre, Tarrach, Rolf
openaire +5 more sources
Robust Subspace Learning: Robust PCA, Robust Subspace Tracking, and Robust Subspace Recovery [PDF]
IEEE Signal Processing Magazine, 2018 To appear, IEEE Signal Processing Magazine, July ...
Namrata Vaswani +3 more
openaire +4 more sources