Follow
Fatemehsadat Mireshghallah
Title
Cited by
Cited by
Year
Releq: A reinforcement learning approach for deep quantization of neural networks
AT Elthakeb, P Pilligundla, FS Mireshghallah, A Yazdanbakhsh, ...
arXiv preprint arXiv:1811.01704, 2018
95*2018
Privacy in deep learning: A survey
F Mireshghallah, M Taram, P Vepakomma, A Singh, R Raskar, ...
arXiv preprint arXiv:2004.12254, 2020
572020
Shredder: Learning noise distributions to protect inference privacy
F Mireshghallah, M Taram, P Ramrakhyani, A Jalali, D Tullsen, ...
Proceedings of the Twenty-Fifth International Conference on Architectural …, 2020
49*2020
Neither private nor fair: Impact of data imbalance on utility and fairness in differential privacy
T Farrand, F Mireshghallah, S Singh, A Trask
Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in …, 2020
312020
Not all features are equal: Discovering essential features for preserving prediction privacy
F Mireshghallah, M Taram, A Jalali, ATT Elthakeb, D Tullsen, ...
Proceedings of the Web Conference 2021, 669-680, 2021
15*2021
Benchmarking differential privacy and federated learning for bert models
P Basu, TS Roy, R Naidu, Z Muftuoglu, S Singh, F Mireshghallah
arXiv preprint arXiv:2106.13973, 2021
142021
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
F Mireshghallah, HA Inan, M Hasegawa, V Rühle, T Berg-Kirkpatrick, ...
Proceedings of the 2021 Conference of the North American Chapter of the …, 2021
142021
Gradient-based deep quantization of neural networks through sinusoidal adaptive regularization
AT Elthakeb, P Pilligundla, F Mireshghallah, T Elgindi, CA Deledalle, ...
arXiv preprint arXiv:2003.00146 1, 2020
9*2020
Energy-efficient permanent fault tolerance in hard real-time systems
FS Mireshghallah, M Bakhshalipour, M Sadrosadati, H Sarbazi-Azad
IEEE Transactions on Computers 68 (10), 1539-1545, 2019
82019
Divide and Conquer: Leveraging intermediate feature representations for quantized training of neural networks
AT Elthakeb, P Pilligundla, F Mireshghallah, A Cloninger, ...
International Conference on Machine Learning, 2880-2891, 2020
72020
What Does it Mean for a Language Model to Preserve Privacy?
H Brown, K Lee, F Mireshghallah, R Shokri, F Tramèr
arXiv preprint arXiv:2202.05520, 2022
62022
DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
A Uniyal, R Naidu, S Kotti, S Singh, PJ Kenfack, F Mireshghallah, A Trask
arXiv preprint arXiv:2106.12576, 2021
62021
Style pooling: Automatic text style obfuscation for improved classification fairness
F Mireshghallah, T Berg-Kirkpatrick
arXiv preprint arXiv:2109.04624, 2021
42021
U-Noise: Learnable Noise Masks for Interpretable Image Segmentation
T Koker, F Mireshghallah, T Titcombe, G Kaissis
arXiv preprint arXiv:2101.05791, 2021
32021
WaveQ: Gradient-based deep quantization of neural networks through sinusoidal adaptive regularization
AT Elthakeb, P Pilligundla, F Mireshghallah, T Elgindi, CA Deledalle, ...
arXiv preprint arXiv:2003.00146, 2020
32020
Mix and Match: Learning-free Controllable Text Generation using Energy Language Models
F Mireshghallah, K Goyal, T Berg-Kirkpatrick
arXiv preprint arXiv:2203.13299, 2022
22022
Quantifying privacy risks of masked language models using membership inference attacks
F Mireshghallah, K Goyal, A Uniyal, T Berg-Kirkpatrick, R Shokri
arXiv preprint arXiv:2203.03929, 2022
22022
UserIdentifier: implicit user representations for simple and effective personalized sentiment analysis
F Mireshghallah, V Shrivastava, M Shokouhi, T Berg-Kirkpatrick, R Sim, ...
arXiv preprint arXiv:2110.00135, 2021
22021
When differential privacy meets interpretability: A case study
R Naidu, A Priyanshu, A Kumar, S Kotti, H Wang, F Mireshghallah
arXiv preprint arXiv:2106.13203, 2021
12021
Methods of providing data privacy for neural network based inference
F Mireshghallah, H Esmaeilzadeh
US Patent App. 17/656,409, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–20