Urmăriți
Huseyin A. Inan
Huseyin A. Inan
Microsoft Research AI
Adresă de e-mail confirmată pe microsoft.com
Titlu
Citat de
Citat de
Anul
Differentially Private Fine-tuning of Language Models
D Yu, S Naik, A Backurs, S Gopi, HA Inan, G Kamath, J Kulkarni, YT Lee, ...
arXiv preprint arXiv:2110.06500, 2021
3622021
Synthetic text generation with differential privacy: A simple and practical recipe
X Yue, HA Inan, X Li, G Kumar, J McAnallen, H Shajari, H Sun, D Levitan, ...
arXiv preprint arXiv:2210.14348, 2022
902022
rTop-k: A Statistical Estimation Approach to Distributed SGD
LP Barnes, HA Inan, B Isik, A Özgür
IEEE Journal on Selected Areas in Information Theory 1 (3), 897-907, 2020
712020
When Does Differentially Private Learning Not Suffer in High Dimensions?
X Li, D Liu, TB Hashimoto, HA Inan, J Kulkarni, YT Lee, A Guha Thakurta
Advances in Neural Information Processing Systems 35, 28616-28630, 2022
622022
Membership Inference Attacks Against NLP Classification Models
V Shejwalkar, HA Inan, A Houmansadr, R Sim
NeurIPS 2021 Workshop Privacy in Machine Learning, 2021
612021
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
X Tang, R Shin, HA Inan, A Manoel, F Mireshghallah, Z Lin, S Gopi, ...
arXiv preprint arXiv:2309.11765, 2023
552023
Training Data Leakage Analysis in Language Models
HA Inan, O Ramadan, L Wutschitz, D Jones, V Rühle, J Withers, R Sim
Privacy Preserving Machine Learning Workshop, 2021
54*2021
On the optimality of the Kautz-Singleton construction in probabilistic group testing
HA Inan, P Kairouz, M Wootters, A Özgür
IEEE Transactions on Information Theory 65 (9), 5592-5603, 2019
512019
Membership Inference on Word Embedding and Beyond
S Mahloujifar, HA Inan, M Chase, E Ghosh, M Hasegawa
arXiv preprint arXiv:2106.11384, 2021
432021
Online power control for the energy harvesting multiple access channel
HA Inan, A Ozgur
2016 14th International Symposium on Modeling and Optimization in Mobile, Ad …, 2016
422016
A convolutive bounded component analysis framework for potentially nonstationary independent and/or dependent sources
HA Inan, AT Erdogan
IEEE Transactions on Signal Processing 63 (1), 18-30, 2014
422014
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
F Mireshghallah, HA Inan, M Hasegawa, V Rühle, T Berg-Kirkpatrick, ...
arXiv preprint arXiv:2103.07567, 2021
402021
Convolutive bounded component analysis algorithms for independent and dependent source separation
HA Inan, AT Erdogan
IEEE transactions on neural networks and learning systems 26 (4), 697-708, 2014
402014
Sparse group testing codes for low-energy massive random access
HA Inan, P Kairouz, A Ozgur
2017 55th Annual Allerton Conference on Communication, Control, and …, 2017
302017
An extended family of bounded component analysis algorithms
HA Inan, AT Erdogan
2014 48th Asilomar Conference on Signals, Systems and Computers, 442-445, 2014
292014
A Group Testing Approach to Random Access for Short-Packet Communication
HA Inan, S Ahn, P Kairouz, A Ozgur
2019 IEEE International Symposium on Information Theory (ISIT), 96-100, 2019
272019
Sparse combinatorial group testing
HA Inan, P Kairouz, A Özgür
IEEE Transactions on Information Theory 66 (5), 2729-2742, 2019
252019
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
C Xie, Z Lin, A Backurs, S Gopi, D Yu, HA Inan, H Nori, H Jiang, H Zhang, ...
arXiv preprint arXiv:2403.01749, 2024
232024
Differentially private model compression
F Mireshghallah, A Backurs, HA Inan, L Wutschitz, J Kulkarni
Advances in Neural Information Processing Systems 35, 29468-29483, 2022
232022
Capacity of the energy harvesting Gaussian MAC
HA Inan, D Shaviv, A Özgür
IEEE Transactions on Information Theory 64 (4), 2347-2360, 2018
202018
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20