Privacy Regularization: Joint Privacy-Utility Optimization in Language Models

12 March 2021

Fatemehsadat Mireshghallah

Huseyin A. Inan

Marcello Hasegawa

Victor Rühle

Taylor Berg-Kirkpatrick

Robert Sim

ArXiv PDF HTML

Papers citing "Privacy Regularization: Joint Privacy-Utility Optimization in Language Models"

24 / 24 papers shown

Title
Adanonymizer: Interactively Navigating and Balancing the Duality of Privacy and Output Performance in Human-LLM Interaction Shuning Zhang Xin Yi Haobin Xing Lyumanshan Ye Yongquan Hu Hewu Li 34 2 0 19 Oct 2024
Natural Language but Omitted? On the Ineffectiveness of Large Language Models' privacy policy from End-users' Perspective Shuning Zhang Haobin Xing Xin Yi Hewu Li PILM 48 0 0 26 Jun 2024
Reconstructing training data from document understanding models Jérémie Dentan Arnaud Paran A. Shabou AAML SyDa 41 1 0 05 Jun 2024
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs Charlie Hou Akshat Shrivastava Hongyuan Zhan Rylan Conway Trang Le Adithya Sagar Giulia Fanti Daniel Lazar 30 8 0 05 Jun 2024
Navigating LLM Ethics: Advancements, Challenges, and Future Directions Junfeng Jiao S. Afroogh Yiming Xu Connor Phillips AILaw 62 19 0 14 May 2024
Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration Wenjie Fu Huandong Wang Chen Gao Guanghua Liu Yong Li Tao Jiang MIALM 24 43 0 10 Nov 2023
Using Property Elicitation to Understand the Impacts of Fairness Regularizers Jessie Finocchiaro FaML 32 0 0 20 Sep 2023
Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models Adel M. Elmahdy A. Salem SILM 17 6 0 23 Jun 2023
Membership Inference Attacks against Language Models via Neighbourhood Comparison Justus Mattern Fatemehsadat Mireshghallah Zhijing Jin Bernhard Schölkopf Mrinmaya Sachan Taylor Berg-Kirkpatrick MIALM 23 167 0 29 May 2023
Training Data Extraction From Pre-trained Language Models: A Survey Shotaro Ishihara 24 46 0 25 May 2023
Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization Aman Priyanshu Supriti Vijay Ayush Kumar Rakshit Naidu Fatemehsadat Mireshghallah SILM 30 24 0 24 May 2023
Watermarking Text Data on Large Language Models for Dataset Copyright Yixin Liu Hongsheng Hu Xun Chen Xuyun Zhang Lichao Sun WaLM 19 22 0 22 May 2023
A Customized Text Sanitization Mechanism with Differential Privacy Hui Chen Fengran Mo Yanhao Wang Cen Chen J. Nie Chengyu Wang Jamie Cui 11 34 0 04 Jul 2022
Privacy Leakage in Text Classification: A Data Extraction Approach Adel M. Elmahdy Huseyin A. Inan Robert Sim 21 13 0 09 Jun 2022
You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas Haoran Li Yangqiu Song Lixin Fan 59 19 0 26 Apr 2022
Mix and Match: Learning-free Controllable Text Generation using Energy Language Models Fatemehsadat Mireshghallah Kartik Goyal Taylor Berg-Kirkpatrick 36 78 0 24 Mar 2022
Do Language Models Plagiarize? Jooyoung Lee Thai Le Jinghui Chen Dongwon Lee 30 74 0 15 Mar 2022
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks Fatemehsadat Mireshghallah Kartik Goyal Archit Uniyal Taylor Berg-Kirkpatrick Reza Shokri MIALM 32 151 0 08 Mar 2022
Deduplicating Training Data Mitigates Privacy Risks in Language Models Nikhil Kandpal Eric Wallace Colin Raffel PILM MU 36 274 0 14 Feb 2022
Submix: Practical Private Prediction for Large-Scale Language Models Antonio A. Ginart L. V. D. van der Maaten James Zou Chuan Guo 30 22 0 04 Jan 2022
Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness Fatemehsadat Mireshghallah Taylor Berg-Kirkpatrick 20 11 0 10 Sep 2021
Benchmarking Differential Privacy and Federated Learning for BERT Models Priya Basu Tiasa Singha Roy Rakshit Naidu Zumrut Muftuoglu Sahib Singh Fatemehsadat Mireshghallah FedML AI4MH 18 49 0 26 Jun 2021
Membership Inference on Word Embedding and Beyond Saeed Mahloujifar Huseyin A. Inan Melissa Chase Esha Ghosh Marcello Hasegawa MIACV SILM 22 46 0 21 Jun 2021
Extracting Training Data from Large Language Models Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown D. Song Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 290 1,815 0 14 Dec 2020