Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Sinha, Amer"'
Autor:
Chua, Lynn, Ghazi, Badih, Huang, Yangsibo, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Sinha, Amer, Xie, Chulin, Zhang, Chiyuan
Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, effectively being crosslingual? This study evaluates six state-of-the-art
Externí odkaz:
http://arxiv.org/abs/2406.16135
Autor:
Chua, Lynn, Ghazi, Badih, Huang, Yangsibo, Kamath, Pritish, Kumar, Ravi, Liu, Daogao, Manurangsi, Pasin, Sinha, Amer, Zhang, Chiyuan
Large language models (LLMs) have emerged as powerful tools for tackling complex tasks across diverse domains, but they also raise privacy concerns when fine-tuned on sensitive data due to potential memorization. While differential privacy (DP) offer
Externí odkaz:
http://arxiv.org/abs/2406.14322
Autor:
Chua, Lynn, Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Sinha, Amer, Zhang, Chiyuan
We demonstrate a substantial gap between the privacy guarantees of the Adaptive Batch Linear Queries (ABLQ) mechanism under different types of batch sampling: (i) Shuffling, and (ii) Poisson subsampling; the typical analysis of Differentially Private
Externí odkaz:
http://arxiv.org/abs/2403.17673
Autor:
Chua, Lynn, Cui, Qiliang, Ghazi, Badih, Harrison, Charlie, Kamath, Pritish, Krichene, Walid, Kumar, Ravi, Manurangsi, Pasin, Narra, Krishna Giri, Sinha, Amer, Varadarajan, Avinash, Zhang, Chiyuan
Motivated by problems arising in digital advertising, we introduce the task of training differentially private (DP) machine learning models with semi-sensitive features. In this setting, a subset of the features is known to the attacker (and thus nee
Externí odkaz:
http://arxiv.org/abs/2401.15246
Autor:
Ghazi, Badih, Huang, Yangsibo, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Sinha, Amer, Zhang, Chiyuan
As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient descent, has
Externí odkaz:
http://arxiv.org/abs/2311.08357
Autor:
Denison, Carson, Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Narra, Krishna Giri, Sinha, Amer, Varadarajan, Avinash V, Zhang, Chiyuan
A well-known algorithm in privacy-preserving ML is differentially private stochastic gradient descent (DP-SGD). While this algorithm has been evaluated on text and image data, it has not been previously applied to ads data, which are notorious for th
Externí odkaz:
http://arxiv.org/abs/2211.11896
The shuffle model of differential privacy has attracted attention in the literature due to it being a middle ground between the well-studied central and local models. In this work, we study the problem of summing (aggregating) real numbers or integer
Externí odkaz:
http://arxiv.org/abs/2109.13158
Publikováno v:
Ghazi, B, Kumar, R, Manurangsi, P, Pagh, R & Sinha, A 2021, Differentially Private Aggregation in the Shuffle Model : Almost Central Accuracy in Almost a Single Message . in M Meila & T Zhang (eds), Proceedings of the 38 th International Conference on Machine Learning . PMLR, Proceedings of Machine Learning Research, vol. 139, pp. 3692-3701, 38th International Conference on Machine Learning (ICML), Virtual, 18/07/2021 . < https://proceedings.mlr.press/v139/ >
The shuffle model of differential privacy has attracted attention in the literature due to it being a middle ground between the well-studied central and local models. In this work, we study the problem of summing (aggregating) real numbers or integer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2751::7df063838393d151229790209bf11eb5
https://curis.ku.dk/portal/da/publications/differentially-private-aggregation-in-the-shuffle-model(29340b4d-5f69-4709-b336-03b32d9ae8cb).html
https://curis.ku.dk/portal/da/publications/differentially-private-aggregation-in-the-shuffle-model(29340b4d-5f69-4709-b336-03b32d9ae8cb).html