v1v2 (latest)

Differentially Private Decoding in Large Language Models

26 May 2022

Papers citing "Differentially Private Decoding in Large Language Models"

31 / 31 papers shown

Title
MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction Sepideh Abedini Shubhankar Mohapatra D. B. Emerson Masoumeh Shafieinejad Jesse C. Cresswell Xi He 146 0 0 27 Sep 2025
Privacy Preserving In-Context-Learning Framework for Large Language Models Bishnu Bhusal Manoj Acharya R. Kaur Colin Samplawski Anirban Roy Adam D. Cobb Rohit Chadha Susmit Jha SyDa 324 0 0 17 Sep 2025
DP-Fusion: Token-Level Differentially Private Inference for Large Language Models Rushil Thareja Preslav Nakov Praneeth Vepakomma Nils Lukas 194 0 0 06 Jul 2025
InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy Vishnu Vinod Krishna Pillutla Abhradeep Thakurta SILM SyDa 102 1 0 30 Jun 2025
Clustering and Median Aggregation Improve Differentially Private Inference Kareem Amin Salman Avestimehr Sara Babakniya Alex Bie Weiwei Kong Natalia Ponomareva Umar Syed 256 5 0 05 Jun 2025
Ontology- and LLM-based Data Harmonization for Federated Learning in Healthcare Natallia Kokash Lei Wang Thomas H. Gillespie Adam Belloum Paola Grosso Sara Quinney Lang Li Bernard de Bono 179 6 0 26 May 2025
How Private is Your Attention? Bridging Privacy with In-Context Learning Soham Bonnerjee Zhen Wei Yeon Anna Asch Sagnik Nandy Promit Ghosal 313 0 0 22 Apr 2025
Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model UtilityInternational Conference on Learning Representations (ICLR), 2025 Martin Kuo Jingyang Zhang Jianyi Zhang Minxue Tang Louis DiValentin ... William Chen Amin Hass Tianlong Chen Yuxiao Chen Haoyang Li MU KELM 374 7 0 24 Feb 2025
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational AgentsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Ivoline Ngong Swanand Kadhe Hao Wang K. Murugesan Justin D. Weisz Amit Dhurandhar Karthikeyan N. Ramamurthy 251 12 0 22 Feb 2025
A Practical and Privacy-Preserving Framework for Real-World Large Language Model Services Yu Mao Xueping Liao Wei Liu Anjia Yang 129 0 0 03 Nov 2024
Data-adaptive Differentially Private Prompt Synthesis for In-Context LearningInternational Conference on Learning Representations (ICLR), 2024 Fengyu Gao Ruida Zhou T. Wang Cong Shen Jing Yang 261 5 0 15 Oct 2024
Adaptively Private Next-Token Prediction of Large Language Models James Flemings Meisam Razaviyayn Murali Annavaram 404 3 0 02 Oct 2024
Private prediction for large-scale synthetic text generation Kareem Amin Alex Bie Weiwei Kong Alexey Kurakin Natalia Ponomareva Umar Syed Seth Neel Sergei Vassilvitskii SyDa SILM 363 16 0 16 Jul 2024
ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets Ahmed Frikha Nassim Walha Ricardo Mendes Krishna Kanth Nakka Xue Jiang Xuebing Zhou 358 4 0 03 Jul 2024
Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation Maya Anderson Guy Amit Abigail Goldsteen AAML 322 39 0 30 May 2024
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language ModelsInternational Conference on Machine Learning (ICML), 2024 George-Octavian Barbulescu Peter Triantafillou MU 329 32 0 06 May 2024
On Protecting the Data Privacy of Large Language Models (LLMs): A SurveyInternational Conference on Mathematics and Computing (ICMC), 2024 Biwei Yan Kun Li Minghui Xu Yueyan Dong Yue Zhang Zhaochun Ren Xiuzhen Cheng AILaw PILM 376 152 0 08 Mar 2024
Privacy-Preserving Instructions for Aligning Large Language Models Da Yu Peter Kairouz Sewoong Oh Zheng Xu 444 34 0 21 Feb 2024
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems Tianyu Cui Yanling Wang Chuanpu Fu Yong Xiao Sijia Li ... Junwu Xiong Xinyu Kong ZuJie Wen Ke Xu Qi Li 308 98 0 11 Jan 2024
A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the UglyHigh-Confidence Computing (HC), 2023 Yifan Yao Jinhao Duan Kaidi Xu Yuanfang Cai Eric Sun Yue Zhang PILM ELM 546 907 0 04 Dec 2023
Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey Victoria Smith Ali Shahin Shamsabadi Carolyn Ashurst Adrian Weller PILM 436 41 0 27 Sep 2023
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot GenerationInternational Conference on Learning Representations (ICLR), 2023 Xinyu Tang Richard Shin Huseyin A. Inan Andre Manoel Fatemehsadat Mireshghallah Zinan Lin Sivakanth Gopi Janardhan Kulkarni Robert Sim 382 89 0 21 Sep 2023
"It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational AgentsInternational Conference on Human Factors in Computing Systems (CHI), 2023 Zhiping Zhang Michelle Jia Hao-Ping Lee Bingsheng Yao Sauvik Das Ada Lerner Dakuo Wang Tianshi Li SILM ELM 278 120 0 20 Sep 2023
Controlling the Extraction of Memorized Data from Large Language Models via Prompt-TuningAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Mustafa Safa Ozdayi Charith Peris Jack G. M. FitzGerald Christophe Dupuy Jimit Majmudar Haidar Khan Rahil Parikh Rahul Gupta 213 42 0 19 May 2023
Auditing and Generating Synthetic Data with Controllable Trust Trade-offsIEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS), 2023 Brian M. Belgodere Pierre Dognin Adam Ivankay Igor Melnyk Youssef Mroueh ... Mattia Rigotti Jerret Ross Yair Schiff Radhika Vedpathak Richard A. Young 445 17 0 21 Apr 2023
Differentially Private Natural Language Models: Recent Advances and Future DirectionsFindings (Findings), 2023 Lijie Hu Ivan Habernal Lei Shen Haiyan Zhao AAML 220 23 0 22 Jan 2023
Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable SurveyConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 Sachin Kumar Vidhisha Balachandran Lucille Njoo Antonios Anastasopoulos Yulia Tsvetkov ELM 406 105 0 14 Oct 2022
Knowledge Unlearning for Mitigating Privacy Risks in Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Joel Jang Dongkeun Yoon Sohee Yang Sungmin Cha Moontae Lee Lajanugen Logeswaran Minjoon Seo KELM PILM MU 466 337 0 04 Oct 2022
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model Saleh Soltan Shankar Ananthakrishnan Jack G. M. FitzGerald Rahul Gupta Wael Hamza ... Mukund Sridhar Fabian Triefenbach Apurv Verma Gokhan Tur Premkumar Natarajan 346 89 0 02 Aug 2022
Differentially Private Model CompressionNeural Information Processing Systems (NeurIPS), 2022 Fatemehsadat Mireshghallah A. Backurs Huseyin A. Inan Lukas Wutschitz Janardhan Kulkarni SyDa 147 16 0 03 Jun 2022
What Neural Networks Memorize and Why: Discovering the Long Tail via Influence EstimationNeural Information Processing Systems (NeurIPS), 2020 Vitaly Feldman Chiyuan Zhang TDI 518 560 0 09 Aug 2020