Huseyin Atahan Inan

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 Project

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 Project

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 Project

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 Project

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

Xiang Yue, Huseyin Inan, Xuechen Li, Girish Kumar, Julia McAnallen, Huan Sun, David Levitan, Robert Sim

ACL 2023 | July 2023

Publication

Differentially Private Model Compression

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

NeurIPS 2022 | November 2022

Publication Project

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 Project

dp-transformers: Training transformer models with differential privacy

Huseyin Inan, Andre Manoel, Lukas Wutschitz

July 2022

Publication Project

Active Data Pattern Extraction Attacks on Generative Language Models

Esha Ghosh, Bargav Jayaraman, Sambuddha Roy, Wei Dai, Huseyin Inan, Melissa Chase

MSR-TR-2022-23 | July 2022

Published by Microsoft

Publication

Privacy Leakage in Text Classification: A Data Extraction Approach

Adel Elmahdy, Huseyin Inan, Robert Sim

June 2022

Publication

Membership Inference Attacks Against NLP Classification Models

Virat Shejwalkar, Huseyin Inan, Amir Houmansadr, Robert Sim

NeurIPS 2021 Workshop Privacy in Machine Learning | September 2021

Publication

Membership Inference on Word Embedding and Beyond

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

June 2021

Preprint

On Privacy and Confidentiality of Communications in Organizational Graphs

Masoumeh Shafieinejad, Huseyin A. Inan (huinan), Marcello Hasegawa, Robert Sim

May 2021

Publication

Training Data Leakage Analysis in Language Models

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

February 2021

Preprint

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 Project

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 Project

Differentially Private Model Compression

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

NeurIPS 2022 | November 2022

Publication Project

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 Project

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 Project

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 Project

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 Project

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 Project

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

Xiang Yue, Huseyin Inan, Xuechen Li, Girish Kumar, Julia McAnallen, Huan Sun, David Levitan, Robert Sim

ACL 2023 | July 2023

Publication

Differentially Private Model Compression

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

NeurIPS 2022 | November 2022

Publication Project

dp-transformers: Training transformer models with differential privacy

Huseyin Inan, Andre Manoel, Lukas Wutschitz

July 2022

Publication Project

Active Data Pattern Extraction Attacks on Generative Language Models

Esha Ghosh, Bargav Jayaraman, Sambuddha Roy, Wei Dai, Huseyin Inan, Melissa Chase

MSR-TR-2022-23 | July 2022

Published by Microsoft

Publication

Membership Inference Attacks Against NLP Classification Models

Virat Shejwalkar, Huseyin Inan, Amir Houmansadr, Robert Sim

NeurIPS 2021 Workshop Privacy in Machine Learning | September 2021

Publication

Membership Inference on Word Embedding and Beyond

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

June 2021

Preprint

On Privacy and Confidentiality of Communications in Organizational Graphs

Masoumeh Shafieinejad, Huseyin A. Inan (huinan), Marcello Hasegawa, Robert Sim

May 2021

Publication

Training Data Leakage Analysis in Language Models

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

February 2021

Preprint

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 Project

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 Project

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 Project

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

Xiang Yue, Huseyin Inan, Xuechen Li, Girish Kumar, Julia McAnallen, Huan Sun, David Levitan, Robert Sim

ACL 2023 | July 2023

Publication

dp-transformers: Training transformer models with differential privacy

Huseyin Inan, Andre Manoel, Lukas Wutschitz

July 2022

Publication Project

Active Data Pattern Extraction Attacks on Generative Language Models

Esha Ghosh, Bargav Jayaraman, Sambuddha Roy, Wei Dai, Huseyin Inan, Melissa Chase

MSR-TR-2022-23 | July 2022

Published by Microsoft

Publication

Privacy Leakage in Text Classification: A Data Extraction Approach

Adel Elmahdy, Huseyin Inan, Robert Sim

June 2022

Publication

Membership Inference on Word Embedding and Beyond

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

June 2021

Preprint

On Privacy and Confidentiality of Communications in Organizational Graphs

Masoumeh Shafieinejad, Huseyin A. Inan (huinan), Marcello Hasegawa, Robert Sim

May 2021

Publication

Training Data Leakage Analysis in Language Models

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

February 2021

Preprint

Membership Inference on Word Embedding and Beyond

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

June 2021

Preprint

On Privacy and Confidentiality of Communications in Organizational Graphs

Masoumeh Shafieinejad, Huseyin A. Inan (huinan), Marcello Hasegawa, Robert Sim

May 2021

Publication

Training Data Leakage Analysis in Language Models

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

February 2021

Preprint

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 Project

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 Project

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 Project

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 Project

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

Xiang Yue, Huseyin Inan, Xuechen Li, Girish Kumar, Julia McAnallen, Huan Sun, David Levitan, Robert Sim

ACL 2023 | July 2023

Publication

Differentially Private Model Compression

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

NeurIPS 2022 | November 2022

Publication Project

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 Project

Membership Inference Attacks Against NLP Classification Models

Virat Shejwalkar, Huseyin Inan, Amir Houmansadr, Robert Sim

NeurIPS 2021 Workshop Privacy in Machine Learning | September 2021

Publication

dp-transformers: Training transformer models with differential privacy

Huseyin Inan, Andre Manoel, Lukas Wutschitz

July 2022

Publication Project

Membership Inference on Word Embedding and Beyond

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

June 2021

Preprint

Training Data Leakage Analysis in Language Models

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

February 2021

Preprint

Active Data Pattern Extraction Attacks on Generative Language Models

Esha Ghosh, Bargav Jayaraman, Sambuddha Roy, Wei Dai, Huseyin Inan, Melissa Chase

MSR-TR-2022-23 | July 2022

Published by Microsoft

Publication

Privacy Leakage in Text Classification: A Data Extraction Approach

Adel Elmahdy, Huseyin Inan, Robert Sim

June 2022

Publication

On Privacy and Confidentiality of Communications in Organizational Graphs

Masoumeh Shafieinejad, Huseyin A. Inan (huinan), Marcello Hasegawa, Robert Sim

May 2021

Publication