Search Results for author: Archit Uniyal

Found 3 papers, 2 papers with code

Memorization in NLP Fine-tuning Methods

1 code implementation25 May 2022 FatemehSadat Mireshghallah, Archit Uniyal, Tianhao Wang, David Evans, Taylor Berg-Kirkpatrick

Large language models are shown to present privacy risks through memorization of training data, and several recent works have studied such risks for the pre-training phase.

Memorization

Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks

no code implementations8 Mar 2022 FatemehSadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, Reza Shokri

The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information about their training data?

Inference Attack Membership Inference Attack +1

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

1 code implementation22 Jun 2021 Archit Uniyal, Rakshit Naidu, Sasikanth Kotti, Sahib Singh, Patrik Joslin Kenfack, FatemehSadat Mireshghallah, Andrew Trask

Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on different sub-groups in the population, which leads to a significantly high drop-in model utility for sub-populations that are under-represented (minorities), compared to well-represented ones.

Fairness

Cannot find the paper you are looking for? You can Submit a new open access paper.