Understanding Unintended Memorization in Federated Learning

12 June 2020

Om Thakkar

Swaroop Indra Ramaswamy

Papers citing "Understanding Unintended Memorization in Federated Learning"

50 / 59 papers shown

Title
Efficiently Attacking Memorization Scores Tue Do Varun Chandrasekaran Daniel Alabi TDI AAML 242 0 0 24 Sep 2025
Fairness in Federated Learning: Fairness for Whom? Afaf Taik Khaoula Chehbouni G. Farnadi FedML 185 1 0 27 May 2025
FedSEA-LLaMA: A Secure, Efficient and Adaptive Federated Splitting Framework for Large Language Models Zishuai Zhang Hainan Zhang JiaYing Zheng Ziwei Wang Jin Dong Yongxin Tong Zhiming Zheng FedML 368 0 0 21 May 2025
Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Models Sunny Duan Mikail Khona Abhiram Iyer Rylan Schaeffer Ila R Fiete 354 5 0 20 Jun 2024
Memorization in deep learning: A survey Jiaheng Wei Yanjun Zhang Leo Yu Zhang Ming Ding Chao Chen Kok-Leong Ong Jun Zhang Yang Xiang 273 15 0 06 Jun 2024
Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models Martin Riddell Ansong Ni Arman Cohan ELM 182 45 0 06 Mar 2024
Copyright Traps for Large Language Models Matthieu Meeus Igor Shilov Manuel Faysse Yves-Alexandre de Montjoye 323 37 0 14 Feb 2024
Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two BenchmarksNorth American Chapter of the Association for Computational Linguistics (NAACL), 2023 Ting-Yun Chang Jesse Thomason Robin Jia 263 24 0 15 Nov 2023
SoK: Memorisation in machine learning Dmitrii Usynin Moritz Knolle Georgios Kaissis 285 1 0 06 Nov 2023
Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering Md Rafi Ur Rashid Vishnu Asutosh Dasu Kang Gu Najrin Sultana Shagufta Mehnaz AAML FedML 476 14 0 24 Oct 2023
MoPe: Model Perturbation-based Privacy Attacks on Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Marvin Li Jason Wang Jeffrey G. Wang Seth Neel AAML 235 26 0 22 Oct 2023
Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey Victoria Smith Ali Shahin Shamsabadi Carolyn Ashurst Adrian Weller PILM 416 41 0 27 Sep 2023
A Note On Interpreting Canary Exposure Matthew Jagielski 219 5 0 31 May 2023
Quantifying Overfitting: Evaluating Neural Network Performance through Analysis of Null Space Hossein Rezaei Mohammad Sabokrou 182 5 0 30 May 2023
PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language ModelsRecent Advances in Natural Language Processing (RANLP), 2023 Leonardo Ranaldi Elena Sofia Ruzzetti Fabio Massimo Zanzotto 146 7 0 08 May 2023
Memorization of Named Entities in Fine-tuned BERT ModelsInternational Cross-Domain Conference on Machine Learning and Knowledge Extraction (CD-MAKE), 2022 Andor Diera N. Lell Aygul Garifullina A. Scherp 167 2 0 07 Dec 2022
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated LearningInternational Conference on Learning Representations (ICLR), 2022 Samuel Maddock Alexandre Sablayrolles Pierre Stock FedML 285 28 0 06 Oct 2022
Recitation-Augmented Language ModelsInternational Conference on Learning Representations (ICLR), 2022 Zhiqing Sun Xuezhi Wang Yi Tay Yiming Yang Denny Zhou RALM 665 76 0 04 Oct 2022
Measuring Forgetting of Memorized Training ExamplesInternational Conference on Learning Representations (ICLR), 2022 Matthew Jagielski Om Thakkar Florian Tramèr Daphne Ippolito Katherine Lee ... Eric Wallace Shuang Song Abhradeep Thakurta Nicolas Papernot Chiyuan Zhang TDI 356 132 0 30 Jun 2022
Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language ModelsNeural Information Processing Systems (NeurIPS), 2022 Kushal Tirumala Aram H. Markosyan Luke Zettlemoyer Armen Aghajanyan TDI 319 237 0 22 May 2022
Recovering Private Text in Federated Learning of Language ModelsNeural Information Processing Systems (NeurIPS), 2022 Samyak Gupta Yangsibo Huang Zexuan Zhong Tianyu Gao Kai Li Danqi Chen FedML 251 94 0 17 May 2022
Detecting Unintended Memorization in Language-Model-Fused ASRInterspeech (Interspeech), 2022 Wenjie Huang Steve Chien Om Thakkar Rajiv Mathews 168 11 0 20 Apr 2022
Extracting Targeted Training Data from ASR Models, and How to Mitigate ItInterspeech (Interspeech), 2022 Ehsan Amid Om Thakkar A. Narayanan Rajiv Mathews Franccoise Beaufays 174 11 0 18 Apr 2022
Quantifying Memorization Across Neural Language ModelsInternational Conference on Learning Representations (ICLR), 2022 Nicholas Carlini Daphne Ippolito Matthew Jagielski Katherine Lee Florian Tramèr Chiyuan Zhang PILM 476 760 0 15 Feb 2022
Towards Multi-Objective Statistically Fair Federated Learning Ninareh Mehrabi Cyprien de Lichy John McKay C. He William Campbell FedML 144 12 0 24 Jan 2022
Counterfactual Memorization in Neural Language ModelsNeural Information Processing Systems (NeurIPS), 2021 Chiyuan Zhang Daphne Ippolito Katherine Lee Matthew Jagielski Florian Tramèr Nicholas Carlini 279 167 0 24 Dec 2021
DP-REC: Private & Communication-Efficient Federated Learning Aleksei Triastcyn M. Reisser Christos Louizos FedML 153 18 0 09 Nov 2021
Federated Learning Meets Natural Language Processing: A Survey Ming Liu Stella Ho Mengqi Wang Longxiang Gao Yuan Jin Heng Zhang FedML 142 82 0 27 Jul 2021
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter RatesInternational Conference on Machine Learning (ICML), 2021 Steve Chien Prateek Jain Walid Krichene Steffen Rendle Shuang Song Abhradeep Thakurta Li Zhang 139 19 0 20 Jul 2021
A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter ItIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 Trung D. Q. Dang Om Thakkar Swaroop Indra Ramaswamy Rajiv Mathews Peter Chin Franccoise Beaufays FedML 83 10 0 15 Apr 2021
Extracting Training Data from Large Language ModelsUSENIX Security Symposium (USENIX Security), 2020 Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown Basel Alomair Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 1.1K 2,436 0 14 Dec 2020
Training Production Language Models without Memorizing User Data Swaroop Indra Ramaswamy Om Thakkar Rajiv Mathews Galen Andrew H. B. McMahan Franccoise Beaufays FedML 233 95 0 21 Sep 2020
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning Sai Praneeth Karimireddy Martin Jaggi Satyen Kale M. Mohri Sashank J. Reddi Sebastian U. Stich A. Suresh FedML 522 232 0 08 Aug 2020
LinkedIn's Audience Engagements API: A Privacy Preserving Data Analytics System at ScaleJournal of Privacy and Confidentiality (JPC), 2020 Ryan M. Rogers S. Subramaniam Sean Peng D. Durfee Seunghyun Lee Santosh Kumar Kancha Shraddha Sahay P. Ahammad 163 89 0 14 Feb 2020
Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation Ulfar Erlingsson Vitaly Feldman Ilya Mironov A. Raghunathan Shuang Song Kunal Talwar Abhradeep Thakurta 213 88 0 10 Jan 2020
Advances and Open Problems in Federated Learning Peter Kairouz H. B. McMahan Brendan Avent A. Bellet M. Bennis ... Zheng Xu Qiang Yang Felix X. Yu Han Yu Sen Zhao FedML AI4CE 531 7,405 0 10 Dec 2019
Generative Models for Effective ML on Private, Decentralized DatasetsInternational Conference on Learning Representations (ICLR), 2019 S. Augenstein H. B. McMahan Daniel Ramage Swaroop Indra Ramaswamy Peter Kairouz Mingqing Chen Rajiv Mathews Blaise Agüera y Arcas SyDa 270 204 0 15 Nov 2019
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning Sai Praneeth Karimireddy Satyen Kale M. Mohri Sashank J. Reddi Sebastian U. Stich A. Suresh FedML 307 383 0 14 Oct 2019
Federated Learning of N-gram Language ModelsConference on Computational Natural Language Learning (CoNLL), 2019 Mingqing Chen A. Suresh Rajiv Mathews Adeline Wong Cyril Allauzen F. Beaufays Michael Riley FedML 191 78 0 08 Oct 2019
Federated Learning for Emoji Prediction in a Mobile Keyboard Swaroop Indra Ramaswamy Rajiv Mathews Kanishka Rao Franccoise Beaufays FedML 217 325 0 11 Jun 2019
Gmail Smart Compose: Real-Time Assisted WritingKnowledge Discovery and Data Mining (KDD), 2019 Mengzhao Chen Benjamin Lee G. Bansal Yuan Cao Shuyuan Zhang ... Yinan Wang Andrew M. Dai Zhiwen Chen Timothy Sohn Yonghui Wu 210 224 0 17 May 2019
Differentially Private Learning with Adaptive ClippingNeural Information Processing Systems (NeurIPS), 2019 Galen Andrew Om Thakkar H. B. McMahan Swaroop Ramaswamy FedML 424 389 0 09 May 2019
Towards Federated Learning at Scale: System Design Keith Bonawitz Hubert Eichner W. Grieskamp Dzmitry Huba A. Ingerman ... H. B. McMahan Timon Van Overveldt David Petrou Daniel Ramage Jason Roselander FedML 420 2,937 0 04 Feb 2019
Federated Learning for Mobile Keyboard Prediction Andrew Straiton Hard Kanishka Rao Zhifeng Lin Swaroop Indra Ramaswamy Youjie Li S. Augenstein Alex Schwing M. Annavaram A. Avestimehr FedML 556 1,693 0 08 Nov 2018
Subsampled Rényi Differential Privacy and Analytical Moments Accountant Yu Wang Borja Balle S. Kasiviswanathan 376 437 0 31 Jul 2018
Exploiting Unintended Feature Leakage in Collaborative Learning Luca Melis Congzheng Song Emiliano De Cristofaro Vitaly Shmatikov FedML 457 1,632 0 10 May 2018
Differentially Private Matrix Completion RevisitedInternational Conference on Machine Learning (ICML), 2017 Prateek Jain Om Thakkar Abhradeep Thakurta FedML 200 34 0 28 Dec 2017
Collecting Telemetry Data Privately Bolin Ding Janardhan Kulkarni Sergey Yekhanin 279 755 0 05 Dec 2017
Learning Differentially Private Recurrent Language Models H. B. McMahan Daniel Ramage Kunal Talwar Li Zhang FedML 239 128 0 18 Oct 2017
Prochlo: Strong Privacy for Analytics in the Crowd Andrea Bittau Ulfar Erlingsson Petros Maniatis Ilya Mironov A. Raghunathan David Lie Mitch Rudominer Ushasree Kode J. Tinnés B. Seefeld 280 287 0 02 Oct 2017