Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Fatemehsadat Mireshghallah

Fatemehsadat Mireshghallah

UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis


Oct 01, 2021
Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis


  Access Paper or Ask Questions

Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness


Sep 10, 2021
Fatemehsadat Mireshghallah, Taylor Berg-Kirkpatrick

* EMNLP 2021 

  Access Paper or Ask Questions

Efficient Hyperparameter Optimization for Differentially Private Deep Learning


Aug 09, 2021
Aman Priyanshu, Rakshit Naidu, Fatemehsadat Mireshghallah, Mohammad Malekzadeh

* 4+1 pages, 4 figures, 1 table 

  Access Paper or Ask Questions

Benchmarking Differential Privacy and Federated Learning for BERT Models


Jun 26, 2021
Priyam Basu, Tiasa Singha Roy, Rakshit Naidu, Zumrut Muftuoglu, Sahib Singh, Fatemehsadat Mireshghallah

* 4 pages, 3 tables, 1 figure 

  Access Paper or Ask Questions

When Differential Privacy Meets Interpretability: A Case Study


Jun 25, 2021
Rakshit Naidu, Aman Priyanshu, Aadith Kumar, Sasikanth Kotti, Haofan Wang, Fatemehsadat Mireshghallah

* 4 pages, 7 figures; Extended abstract presented at RCV-CVPR'21 

  Access Paper or Ask Questions

DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?


Jun 22, 2021
Archit Uniyal, Rakshit Naidu, Sasikanth Kotti, Sahib Singh, Patrik Joslin Kenfack, Fatemehsadat Mireshghallah, Andrew Trask

* 4 pages, 3 images 

  Access Paper or Ask Questions

Privacy Regularization: Joint Privacy-Utility Optimization in Language Models


Mar 12, 2021
Fatemehsadat Mireshghallah, Huseyin A. Inan, Marcello Hasegawa, Victor Rühle, Taylor Berg-Kirkpatrick, Robert Sim

* NAACL-HLT 2021 Paper 

  Access Paper or Ask Questions

U-Noise: Learnable Noise Masks for Interpretable Image Segmentation


Jan 20, 2021
Teddy Koker, Fatemehsadat Mireshghallah, Tom Titcombe, Georgios Kaissis

* Submitted to ICIP. Revision: corrected affiliation 

  Access Paper or Ask Questions

Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy


Oct 03, 2020
Tom Farrand, Fatemehsadat Mireshghallah, Sahib Singh, Andrew Trask

* 5 pages, 5 figures 

  Access Paper or Ask Questions

Privacy in Deep Learning: A Survey


May 09, 2020
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Praneeth Vepakomma, Abhishek Singh, Ramesh Raskar, Hadi Esmaeilzadeh


  Access Paper or Ask Questions

A Principled Approach to Learning Stochastic Representations for Privacy in Deep Neural Inference


Mar 26, 2020
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Ali Jalali, Ahmed Taha Elthakeb, Dean Tullsen, Hadi Esmaeilzadeh


  Access Paper or Ask Questions

Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization


Feb 29, 2020
Ahmed T. Elthakeb, Prannoy Pilligundla, Fatemehsadat Mireshghallah, Tarek Elgindi, Charles-Alban Deledalle, Hadi Esmaeilzadeh

* Preliminary work. Under review 

  Access Paper or Ask Questions

Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge


May 26, 2019
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani, Dean Tullsen, Hadi Esmaeilzadeh


  Access Paper or Ask Questions