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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Planting and Mitigating Memorized Content in Predictive-Text Language Models


Dec 16, 2022
C. M. Downey, Wei Dai, Huseyin A. Inan, Kim Laine, Saurabh Naik, Tomasz Religa

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe


Oct 25, 2022
Xiang Yue, Huseyin A. Inan, Xuechen Li, Girish Kumar, Julia McAnallen, Huan Sun, David Levitan, Robert Sim

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

When Does Differentially Private Learning Not Suffer in High Dimensions?


Jul 09, 2022
Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta

Add code

* 25 pages; v2 fixes typos and formatting 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Privacy Leakage in Text Classification: A Data Extraction Approach


Jun 09, 2022
Adel Elmahdy, Huseyin A. Inan, Robert Sim

Add code

* 8 pages, 4 tables. Accepted at NAACL 2022 Workshop on Privacy in NLP (PrivateNLP) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Differentially Private Fine-tuning of Language Models


Oct 13, 2021
Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A. Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Membership Inference on Word Embedding and Beyond


Jun 21, 2021
Saeed Mahloujifar, Huseyin A. Inan, Melissa Chase, Esha Ghosh, Marcello Hasegawa

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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

Add code

* NAACL-HLT 2021 Paper 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Privacy Analysis in Language Models via Training Data Leakage Report


Jan 14, 2021
Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz, Daniel Jones, Victor Rühle, James Withers, Robert Sim

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

rTop-k: A Statistical Estimation Approach to Distributed SGD


May 21, 2020
Leighton Pate Barnes, Huseyin A. Inan, Berivan Isik, Ayfer Ozgur

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>