Project Laplace

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin

ICML 2024 | July 2024

Spotlight

Publication

Statistic Maximal Leakage

Shuaiqi Wang, Zinan Lin, Giulia Fanti

IEEE International Symposium on Information Theory 2024 | July 2024

Publication

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin

ICLR 2024 | May 2024

Publication Publication Github

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim

ICLR 2024 | May 2024

Publication Publication

Privately Aligning Language Models with Reinforcement Learning

Fan Wu, Huseyin Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan (Jana) Kulkarni, Robert Sim

ICLR 2024 | May 2024

DOI

Efficiently Computing Similarities to Private Datasets

Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski

ICLR 2024 | May 2024

Publication

Selective Pre-training for Private Fine-tuning

Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang

TMLR | May 2024

Publication Publication

Summary Statistic Privacy in Data Sharing

Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti

IEEE Journal on Selected Areas in Information Theory | March 2024

Publication

Differentially Private Training of Mixture of Experts Models

Pierre Tholoniat, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Robert Sim

PPAI-24: The 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence | February 2024

DOI

Advancing differential privacy: where we are now and future directions for real-world deployment

Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Da Yu, Sergey Yekhanin, Huanyu Zhang, Wanrong Zhang

Harvard Data Science Review | January 2024, Vol 6(1)

Publication

Differentially Private Approximate Near Neighbor Counting in High Dimensions

Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan

NeurIPS 2023 | December 2023

Spotlight Presentation

Publication

Training Private and Efficient Language Models with Synthetic Data from LLMs

Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan (Jana) Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang

NeurIPS 2023 SoLaR Workshop | December 2023

Publication

Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks

Ruixiang Tang, Gord Lueck, Rodolfo Quispe, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Xia Hu

Empirical Methods in Natural Language Processing (EMNLP 2023) | October 2023

DOI PDF

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li

NeurIPS 2023 | June 2023

Outstanding Paper Award

Publication

Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping

Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan (Jana) Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian

International Conference on Learning Representations (ICLR) 2023 | May 2023

Publication

Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler

Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian

COLT 2023 | February 2023

Publication

Near-Optimal Correlation Clustering with Privacy

Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski

NeurIPS 2022 | November 2022

Publication PDF

Differentially Private Model Compression

Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin Inan, Lukas Wutschitz, Janardhan (Jana) Kulkarni

NeurIPS 2022 | November 2022

Publication

When does differentially private learning not suffer in high dimensions?

Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin Inan, Janardhan (Jana) Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta

NeurIPS’22 | November 2022

Publication

Private Convex Optimization in General Norms

Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian

SODA 2023 | July 2022

Publication

Differentially private fine-tuning of language models

Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Gautam Kamath, Janardhan (Jana) Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang

ICLR 2022 | April 2022

Publication

Private Convex Optimization via Exponential Mechanism

Sivakanth Gopi, Yin Tat Lee, Daogao Liu

COLT 2022 | March 2022

Publication

Differentially private n-gram extraction

Kunho Kim, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Sergey Yekhanin

NeurIPS 2021 | December 2021

PDF Publication

Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

Harsha Nori, Rich Caruana, Zhiqi Bu, Judy Hanwen Shen, Janardhan (Jana) Kulkarni

2021 International Conference on Machine Learning | July 2021

Publication

Numerical Composition of Differential Privacy

Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz

NeurIPS 2021 | June 2021

Spotlight at NeurIPS 2021.

Preprint Github

Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps

Janardhan (Jana) Kulkarni, Yin Tat Lee, Daogao Liu

NeurIPS 2021 | March 2021

Publication

Differentially Private Correlation Clustering

Mark Bun, Marek Eliás, Janardhan (Jana) Kulkarni

2021 International Conference on Machine Learning | February 2021

Publication

Fast and Memory Efficient Differentially Private-SGD via JL Projections

Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat

NeurIPS 2021 | February 2021

Preprint

Differentially Private Set Union

Sivakanth Gopi, Pankaj Gulhane, Janardhan (Jana) Kulkarni, Judy Hanwen Shen, Milad Shokouhi, Sergey Yekhanin

International Conference on Machine Learning 2020 | July 2020

Contributed talk at TPDP 2020. Also appeared in the Journal of Privacy and Confidentiality (JPC).

Publication Github

Locally Private Hypothesis Selection

Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang

Conference on Learning Theory (COLT) 2020 | July 2020

Publication

Privately Learning Markov Random Fields

Huanyu Zhang, Gautam Kamath, Janardhan (Jana) Kulkarni, Zhiwei Steven Wu

ICML 2020 | July 2020

Publication PDF

Differentially private release of synthetic graphs

Marek Eliáš, Michael Kapralov, Janardhan (Jana) Kulkarni, Yin Tat Lee

2020 Symposium on Discrete Algorithms | January 2020

PDF

Locally Private Gaussian Estimation

Matthew Joseph, Janardhan (Jana) Kulkarni, Jieming Mao, Zhiwei Steven Wu

November 2019

Publication PDF

An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors

Joshua Allen, Bolin Ding, Janardhan (Jana) Kulkarni, Harsha Nori, Olga Ohrimenko, Sergey Yekhanin

NeurIPS 2019 | August 2019

Publication Publication Project

Collecting Telemetry Data Privately

Bolin Ding, Janardhan (Jana) Kulkarni, Sergey Yekhanin

Advances in Neural Information Processing Systems 30 | December 2017

Publication

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin

ICML 2024 | July 2024

Spotlight

Publication

Privately Aligning Language Models with Reinforcement Learning

Fan Wu, Huseyin Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan (Jana) Kulkarni, Robert Sim

ICLR 2024 | May 2024

DOI

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin

ICLR 2024 | May 2024

Publication Publication Github

Efficiently Computing Similarities to Private Datasets

Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski

ICLR 2024 | May 2024

Publication

Selective Pre-training for Private Fine-tuning

Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang

TMLR | May 2024

Publication Publication

Differentially Private Training of Mixture of Experts Models

Pierre Tholoniat, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Robert Sim

PPAI-24: The 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence | February 2024

DOI

Differentially Private Approximate Near Neighbor Counting in High Dimensions

Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan

NeurIPS 2023 | December 2023

Spotlight Presentation

Publication

Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks

Ruixiang Tang, Gord Lueck, Rodolfo Quispe, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Xia Hu

Empirical Methods in Natural Language Processing (EMNLP 2023) | October 2023

DOI PDF

Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler

Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian

COLT 2023 | February 2023

Publication

Near-Optimal Correlation Clustering with Privacy

Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski

NeurIPS 2022 | November 2022

Publication PDF

Differentially Private Model Compression

Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin Inan, Lukas Wutschitz, Janardhan (Jana) Kulkarni

NeurIPS 2022 | November 2022

Publication

When does differentially private learning not suffer in high dimensions?

Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin Inan, Janardhan (Jana) Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta

NeurIPS’22 | November 2022

Publication

Private Convex Optimization in General Norms

Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian

SODA 2023 | July 2022

Publication

Differentially private fine-tuning of language models

Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Gautam Kamath, Janardhan (Jana) Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang

ICLR 2022 | April 2022

Publication

Private Convex Optimization via Exponential Mechanism

Sivakanth Gopi, Yin Tat Lee, Daogao Liu

COLT 2022 | March 2022

Publication

Differentially private n-gram extraction

Kunho Kim, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Sergey Yekhanin

NeurIPS 2021 | December 2021

PDF Publication

Numerical Composition of Differential Privacy

Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz

NeurIPS 2021 | June 2021

Spotlight at NeurIPS 2021.

Preprint Github

Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps

Janardhan (Jana) Kulkarni, Yin Tat Lee, Daogao Liu

NeurIPS 2021 | March 2021

Publication

Differentially Private Correlation Clustering

Mark Bun, Marek Eliás, Janardhan (Jana) Kulkarni

2021 International Conference on Machine Learning | February 2021

Publication

Fast and Memory Efficient Differentially Private-SGD via JL Projections

Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat

NeurIPS 2021 | February 2021

Preprint

Privately Learning Markov Random Fields

Huanyu Zhang, Gautam Kamath, Janardhan (Jana) Kulkarni, Zhiwei Steven Wu

ICML 2020 | July 2020

Publication PDF

Locally Private Hypothesis Selection

Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang

Conference on Learning Theory (COLT) 2020 | July 2020

Publication

Differentially Private Set Union

Sivakanth Gopi, Pankaj Gulhane, Janardhan (Jana) Kulkarni, Judy Hanwen Shen, Milad Shokouhi, Sergey Yekhanin

International Conference on Machine Learning 2020 | July 2020

Contributed talk at TPDP 2020. Also appeared in the Journal of Privacy and Confidentiality (JPC).

Publication Github

Differentially private release of synthetic graphs

Marek Eliáš, Michael Kapralov, Janardhan (Jana) Kulkarni, Yin Tat Lee

2020 Symposium on Discrete Algorithms | January 2020

PDF

Collecting Telemetry Data Privately

Bolin Ding, Janardhan (Jana) Kulkarni, Sergey Yekhanin

Advances in Neural Information Processing Systems 30 | December 2017

Publication

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin

ICML 2024 | July 2024

Spotlight

Publication

Statistic Maximal Leakage

Shuaiqi Wang, Zinan Lin, Giulia Fanti

IEEE International Symposium on Information Theory 2024 | July 2024

Publication

Privately Aligning Language Models with Reinforcement Learning

Fan Wu, Huseyin Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan (Jana) Kulkarni, Robert Sim

ICLR 2024 | May 2024

DOI

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim

ICLR 2024 | May 2024

Publication Publication

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin

ICLR 2024 | May 2024

Publication Publication Github

Summary Statistic Privacy in Data Sharing

Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti

IEEE Journal on Selected Areas in Information Theory | March 2024

Publication

Training Private and Efficient Language Models with Synthetic Data from LLMs

Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan (Jana) Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang

NeurIPS 2023 SoLaR Workshop | December 2023

Publication

Differentially Private Approximate Near Neighbor Counting in High Dimensions

Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan

NeurIPS 2023 | December 2023

Spotlight Presentation

Publication

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li

NeurIPS 2023 | June 2023

Outstanding Paper Award

Publication

Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping

Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan (Jana) Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian

International Conference on Learning Representations (ICLR) 2023 | May 2023

Publication

Near-Optimal Correlation Clustering with Privacy

Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski

NeurIPS 2022 | November 2022

Publication PDF

Differentially Private Model Compression

Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin Inan, Lukas Wutschitz, Janardhan (Jana) Kulkarni

NeurIPS 2022 | November 2022

Publication

Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

Harsha Nori, Rich Caruana, Zhiqi Bu, Judy Hanwen Shen, Janardhan (Jana) Kulkarni

2021 International Conference on Machine Learning | July 2021

Publication

Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps

Janardhan (Jana) Kulkarni, Yin Tat Lee, Daogao Liu

NeurIPS 2021 | March 2021

Publication

Privately Learning Markov Random Fields

Huanyu Zhang, Gautam Kamath, Janardhan (Jana) Kulkarni, Zhiwei Steven Wu

ICML 2020 | July 2020

Publication PDF

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin

ICML 2024 | July 2024

Spotlight

Publication

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin

ICLR 2024 | May 2024

Publication Publication Github

Advancing differential privacy: where we are now and future directions for real-world deployment

Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Da Yu, Sergey Yekhanin, Huanyu Zhang, Wanrong Zhang

Harvard Data Science Review | January 2024, Vol 6(1)

Publication

Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler

Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian

COLT 2023 | February 2023

Publication

Private Convex Optimization in General Norms

Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian

SODA 2023 | July 2022

Publication

Private Convex Optimization via Exponential Mechanism

Sivakanth Gopi, Yin Tat Lee, Daogao Liu

COLT 2022 | March 2022

Publication

Numerical Composition of Differential Privacy

Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz

NeurIPS 2021 | June 2021

Spotlight at NeurIPS 2021.

Preprint Github

Fast and Memory Efficient Differentially Private-SGD via JL Projections

Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat

NeurIPS 2021 | February 2021

Preprint

Locally Private Hypothesis Selection

Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang

Conference on Learning Theory (COLT) 2020 | July 2020

Publication

Differentially Private Set Union

Sivakanth Gopi, Pankaj Gulhane, Janardhan (Jana) Kulkarni, Judy Hanwen Shen, Milad Shokouhi, Sergey Yekhanin

International Conference on Machine Learning 2020 | July 2020

Contributed talk at TPDP 2020. Also appeared in the Journal of Privacy and Confidentiality (JPC).

Publication Github

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin

ICML 2024 | July 2024

Spotlight

Publication

Statistic Maximal Leakage

Shuaiqi Wang, Zinan Lin, Giulia Fanti

IEEE International Symposium on Information Theory 2024 | July 2024

Publication

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim

ICLR 2024 | May 2024

Publication Publication

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin

ICLR 2024 | May 2024

Publication Publication Github

Efficiently Computing Similarities to Private Datasets

Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski

ICLR 2024 | May 2024

Publication

Selective Pre-training for Private Fine-tuning

Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang

TMLR | May 2024

Publication Publication

Summary Statistic Privacy in Data Sharing

Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti

IEEE Journal on Selected Areas in Information Theory | March 2024

Publication

Advancing differential privacy: where we are now and future directions for real-world deployment

Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Da Yu, Sergey Yekhanin, Huanyu Zhang, Wanrong Zhang

Harvard Data Science Review | January 2024, Vol 6(1)

Publication

Differentially Private Approximate Near Neighbor Counting in High Dimensions

Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan

NeurIPS 2023 | December 2023

Spotlight Presentation

Publication

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li

NeurIPS 2023 | June 2023

Outstanding Paper Award

Publication

Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping

Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan (Jana) Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian

International Conference on Learning Representations (ICLR) 2023 | May 2023

Publication

Private Convex Optimization in General Norms

Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian

SODA 2023 | July 2022

Publication

Private Convex Optimization via Exponential Mechanism

Sivakanth Gopi, Yin Tat Lee, Daogao Liu

COLT 2022 | March 2022

Publication

Numerical Composition of Differential Privacy

Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz

NeurIPS 2021 | June 2021

Spotlight at NeurIPS 2021.

Preprint Github

Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps

Janardhan (Jana) Kulkarni, Yin Tat Lee, Daogao Liu

NeurIPS 2021 | March 2021

Publication

Fast and Memory Efficient Differentially Private-SGD via JL Projections

Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat

NeurIPS 2021 | February 2021

Preprint

Privately Learning Markov Random Fields

Huanyu Zhang, Gautam Kamath, Janardhan (Jana) Kulkarni, Zhiwei Steven Wu

ICML 2020 | July 2020

Publication PDF

Locally Private Hypothesis Selection

Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang

Conference on Learning Theory (COLT) 2020 | July 2020

Publication

Differentially Private Set Union

Sivakanth Gopi, Pankaj Gulhane, Janardhan (Jana) Kulkarni, Judy Hanwen Shen, Milad Shokouhi, Sergey Yekhanin

International Conference on Machine Learning 2020 | July 2020

Contributed talk at TPDP 2020. Also appeared in the Journal of Privacy and Confidentiality (JPC).

Publication Github

Locally Private Gaussian Estimation

Matthew Joseph, Janardhan (Jana) Kulkarni, Jieming Mao, Zhiwei Steven Wu

November 2019

Publication PDF

An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors

Joshua Allen, Bolin Ding, Janardhan (Jana) Kulkarni, Harsha Nori, Olga Ohrimenko, Sergey Yekhanin

NeurIPS 2019 | August 2019

Publication Publication Project

Collecting Telemetry Data Privately

Bolin Ding, Janardhan (Jana) Kulkarni, Sergey Yekhanin

Advances in Neural Information Processing Systems 30 | December 2017

Publication

Collecting Telemetry Data Privately

Bolin Ding, Janardhan (Jana) Kulkarni, Sergey Yekhanin

Advances in Neural Information Processing Systems 30 | December 2017

Publication

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin

ICML 2024 | July 2024

Spotlight

Publication

Statistic Maximal Leakage

Shuaiqi Wang, Zinan Lin, Giulia Fanti

IEEE International Symposium on Information Theory 2024 | July 2024

Publication

Privately Aligning Language Models with Reinforcement Learning

Fan Wu, Huseyin Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan (Jana) Kulkarni, Robert Sim

ICLR 2024 | May 2024

DOI

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim

ICLR 2024 | May 2024

Publication Publication

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin

ICLR 2024 | May 2024

Publication Publication Github

Efficiently Computing Similarities to Private Datasets

Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski

ICLR 2024 | May 2024

Publication

Differentially Private Training of Mixture of Experts Models

Pierre Tholoniat, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Robert Sim

PPAI-24: The 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence | February 2024

DOI

Training Private and Efficient Language Models with Synthetic Data from LLMs

Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan (Jana) Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang

NeurIPS 2023 SoLaR Workshop | December 2023

Publication

Differentially Private Approximate Near Neighbor Counting in High Dimensions

Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan

NeurIPS 2023 | December 2023

Spotlight Presentation

Publication

Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks

Ruixiang Tang, Gord Lueck, Rodolfo Quispe, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Xia Hu

Empirical Methods in Natural Language Processing (EMNLP 2023) | October 2023

DOI PDF

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li

NeurIPS 2023 | June 2023

Outstanding Paper Award

Publication

Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping

Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan (Jana) Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian

International Conference on Learning Representations (ICLR) 2023 | May 2023

Publication

Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler

Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian

COLT 2023 | February 2023

Publication

Near-Optimal Correlation Clustering with Privacy

Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski

NeurIPS 2022 | November 2022

Publication PDF

Differentially Private Model Compression

Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin Inan, Lukas Wutschitz, Janardhan (Jana) Kulkarni

NeurIPS 2022 | November 2022

Publication

When does differentially private learning not suffer in high dimensions?

Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin Inan, Janardhan (Jana) Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta

NeurIPS’22 | November 2022

Publication

Private Convex Optimization in General Norms

Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian

SODA 2023 | July 2022

Publication

Differentially private fine-tuning of language models

Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Gautam Kamath, Janardhan (Jana) Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang

ICLR 2022 | April 2022

Publication

Private Convex Optimization via Exponential Mechanism

Sivakanth Gopi, Yin Tat Lee, Daogao Liu

COLT 2022 | March 2022

Publication

Differentially private n-gram extraction

Kunho Kim, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Sergey Yekhanin

NeurIPS 2021 | December 2021

PDF Publication

Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

Harsha Nori, Rich Caruana, Zhiqi Bu, Judy Hanwen Shen, Janardhan (Jana) Kulkarni

2021 International Conference on Machine Learning | July 2021

Publication

Numerical Composition of Differential Privacy

Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz

NeurIPS 2021 | June 2021

Spotlight at NeurIPS 2021.

Preprint Github

Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps

Janardhan (Jana) Kulkarni, Yin Tat Lee, Daogao Liu

NeurIPS 2021 | March 2021

Publication

Differentially Private Correlation Clustering

Mark Bun, Marek Eliás, Janardhan (Jana) Kulkarni

2021 International Conference on Machine Learning | February 2021

Publication

Fast and Memory Efficient Differentially Private-SGD via JL Projections

Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat

NeurIPS 2021 | February 2021

Preprint

Privately Learning Markov Random Fields

Huanyu Zhang, Gautam Kamath, Janardhan (Jana) Kulkarni, Zhiwei Steven Wu

ICML 2020 | July 2020

Publication PDF

Locally Private Hypothesis Selection

Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang

Conference on Learning Theory (COLT) 2020 | July 2020

Publication

Differentially Private Set Union

Sivakanth Gopi, Pankaj Gulhane, Janardhan (Jana) Kulkarni, Judy Hanwen Shen, Milad Shokouhi, Sergey Yekhanin

International Conference on Machine Learning 2020 | July 2020

Contributed talk at TPDP 2020. Also appeared in the Journal of Privacy and Confidentiality (JPC).

Publication Github

Differentially private release of synthetic graphs

Marek Eliáš, Michael Kapralov, Janardhan (Jana) Kulkarni, Yin Tat Lee

2020 Symposium on Discrete Algorithms | January 2020

PDF

An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors

Joshua Allen, Bolin Ding, Janardhan (Jana) Kulkarni, Harsha Nori, Olga Ohrimenko, Sergey Yekhanin

NeurIPS 2019 | August 2019

Publication Publication Project

Collecting Telemetry Data Privately

Bolin Ding, Janardhan (Jana) Kulkarni, Sergey Yekhanin

Advances in Neural Information Processing Systems 30 | December 2017

Publication

Selective Pre-training for Private Fine-tuning

Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang

TMLR | May 2024

Publication Publication

Summary Statistic Privacy in Data Sharing

Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti

IEEE Journal on Selected Areas in Information Theory | March 2024

Publication

Advancing differential privacy: where we are now and future directions for real-world deployment

Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Da Yu, Sergey Yekhanin, Huanyu Zhang, Wanrong Zhang

Harvard Data Science Review | January 2024, Vol 6(1)

Publication

Locally Private Gaussian Estimation

Matthew Joseph, Janardhan (Jana) Kulkarni, Jieming Mao, Zhiwei Steven Wu

November 2019

Publication PDF