v1v2v3 (latest)

The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks

22 February 2018

Papers citing "The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks"

50 / 441 papers shown

Title
Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Prediction Mohamed Suliman D. Leith SILM FedML 81 7 0 30 Oct 2022
LegoNet: A Fast and Exact Unlearning Architecture Sihao Yu Fei Sun Jiafeng Guo Ruqing Zhang Xueqi Cheng MU 78 10 0 28 Oct 2022
Privately Fine-Tuning Large Language Models with Differential Privacy R. Behnia Mohammadreza Ebrahimi Jason L. Pacheco B. Padmanabhan 127 51 0 26 Oct 2022
Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe Xiang Yue Huseyin A. Inan Xuechen Li Girish Kumar Julia McAnallen Hoda Shajari Huan Sun David Levitan Robert Sim 152 86 0 25 Oct 2022
Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano Chuan Guo Alexandre Sablayrolles Maziar Sanjabi FedML 69 17 0 24 Oct 2022
Proof of Unlearning: Definitions and Instantiation Jiasi Weng Shenglong Yao Yuefeng Du Junjie Huang Jian Weng Cong Wang MU 76 14 0 20 Oct 2022
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries Yuxin Wen Arpit Bansal Hamid Kazemi Eitan Borgnia Micah Goldblum Jonas Geiping Tom Goldstein MIACV 119 32 0 19 Oct 2022
Verifiable and Provably Secure Machine Unlearning Thorsten Eisenhofer Doreen Riepel Varun Chandrasekaran Esha Ghosh O. Ohrimenko Nicolas Papernot AAML MU 113 28 0 17 Oct 2022
A General Framework for Auditing Differentially Private Machine Learning Fred Lu Joseph Munoz Maya Fuchs Tyler LeBlond Elliott Zaresky-Williams Edward Raff Francis Ferraro Brian Testa FedML 75 38 0 16 Oct 2022
Mitigating Unintended Memorization in Language Models via Alternating Teaching Zhe Liu Xuedong Zhang Fuchun Peng 70 3 0 13 Oct 2022
Understanding Transformer Memorization Recall Through Idioms Adi Haviv Ido Cohen Jacob Gidron R. Schuster Yoav Goldberg Mor Geva 104 53 0 07 Oct 2022
Recitation-Augmented Language Models Zhiqing Sun Xuezhi Wang Yi Tay Yiming Yang Denny Zhou RALM 275 65 0 04 Oct 2022
Dordis: Efficient Federated Learning with Dropout-Resilient Differential Privacy Zhifeng Jiang Wei Wang Ruichuan Chen 108 8 0 26 Sep 2022
Membership Inference Attacks and Generalization: A Causal Perspective Teodora Baluta Shiqi Shen S. Hitarth Shruti Tople Prateek Saxena OOD MIACV 102 20 0 18 Sep 2022
Private Read Update Write (PRUW) in Federated Submodel Learning (FSL): Communication Efficient Schemes With and Without Sparsification Sajani Vithana S. Ulukus FedML 79 20 0 09 Sep 2022
Algorithms with More Granular Differential Privacy Guarantees Badih Ghazi Ravi Kumar Pasin Manurangsi Thomas Steinke 125 7 0 08 Sep 2022
Data Provenance via Differential Auditing Xin Mu Ming Pang Feida Zhu 36 1 0 04 Sep 2022
Are Attribute Inference Attacks Just Imputation? Bargav Jayaraman David Evans TDI MIACV 97 50 0 02 Sep 2022
Membership Inference Attacks by Exploiting Loss Trajectory Yiyong Liu Zhengyu Zhao Michael Backes Yang Zhang 99 111 0 31 Aug 2022
SNAP: Efficient Extraction of Private Properties with Poisoning Harsh Chaudhari John Abascal Alina Oprea Matthew Jagielski Florian Tramèr Jonathan R. Ullman MIACV 96 33 0 25 Aug 2022
Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment Jie Zhu Leye Wang Xiao Han 87 10 0 11 Aug 2022
Differentially Private Vertical Federated Clustering Zitao Li Tianhao Wang Ninghui Li FedML 101 19 0 02 Aug 2022
ReFRS: Resource-efficient Federated Recommender System for Dynamic and Diversified User Preferences Mubashir Imran Hongzhi Yin Tong Chen Nguyen Quoc Viet Hung Alexander Zhou Kai Zheng 85 72 0 28 Jul 2022
Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices Mingbin Xu Congzheng Song Ye Tian Neha Agrawal Filip Granqvist ... Shiyi Han Yaqiao Deng Leo Liu Anmol Walia Alex Jin FedML 89 22 0 18 Jul 2022
A Customized Text Sanitization Mechanism with Differential Privacy Hui Chen Fengran Mo Yanhao Wang Cen Chen J. Nie Chengyu Wang Jamie Cui 104 36 0 04 Jul 2022
Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset Peter Henderson M. Krass Lucia Zheng Neel Guha Christopher D. Manning Dan Jurafsky Daniel E. Ho AILaw ELM 231 103 0 01 Jul 2022
Measuring Forgetting of Memorized Training Examples Matthew Jagielski Om Thakkar Florian Tramèr Daphne Ippolito Katherine Lee ... Eric Wallace Shuang Song Abhradeep Thakurta Nicolas Papernot Chiyuan Zhang TDI 158 111 0 30 Jun 2022
DP $^2$ -NILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring Shuang Dai Fanlin Meng Qian Wang Xizhong Chen 47 6 0 30 Jun 2022
The Privacy Onion Effect: Memorization is Relative Nicholas Carlini Matthew Jagielski Chiyuan Zhang Nicolas Papernot Andreas Terzis Florian Tramèr PILM MIACV 138 110 0 21 Jun 2022
Reconstructing Training Data from Trained Neural Networks Niv Haim Gal Vardi Gilad Yehudai Ohad Shamir Michal Irani 116 141 0 15 Jun 2022
Disparate Impact in Differential Privacy from Gradient Misalignment Maria S. Esipova Atiyeh Ashari Ghomi Yaqiao Luo Jesse C. Cresswell 108 30 0 15 Jun 2022
Local Identifiability of Deep ReLU Neural Networks: the Theory Joachim Bona-Pellissier Franccois Malgouyres François Bachoc FAtt 114 7 0 15 Jun 2022
Bayesian Estimation of Differential Privacy Santiago Zanella Béguelin Lukas Wutschitz Shruti Tople A. Salem Victor Rühle Andrew Paverd Mohammad Naseri Boris Köpf Daniel Jones 95 40 0 10 Jun 2022
Membership Inference via Backdooring Hongsheng Hu Z. Salcic Gillian Dobbie Jinjun Chen Lichao Sun Xuyun Zhang MIACV 72 31 0 10 Jun 2022
Privacy Leakage in Text Classification: A Data Extraction Approach Adel M. Elmahdy Huseyin A. Inan Robert Sim 74 13 0 09 Jun 2022
Subject Granular Differential Privacy in Federated Learning Virendra J. Marathe Pallika H. Kanani Daniel W. Peterson Guy Steele Jr FedML 64 9 0 07 Jun 2022
Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent Da Yu Gautam Kamath Janardhan Kulkarni Tie-Yan Liu Jian Yin Huishuai Zhang 156 22 0 06 Jun 2022
Differentially Private Model Compression Fatemehsadat Mireshghallah A. Backurs Huseyin A. Inan Lukas Wutschitz Janardhan Kulkarni SyDa 55 14 0 03 Jun 2022
Offline Reinforcement Learning with Differential Privacy Dan Qiao Yu Wang OffRL 121 23 0 02 Jun 2022
Private Federated Submodel Learning with Sparsification Sajani Vithana S. Ulukus FedML 72 10 0 31 May 2022
Differentially Private Decoding in Large Language Models Jimit Majmudar Christophe Dupuy Charith Peris S. Smaili Rahul Gupta R. Zemel 70 31 0 26 May 2022
Memorization in NLP Fine-tuning Methods Fatemehsadat Mireshghallah Archit Uniyal Tianhao Wang David Evans Taylor Berg-Kirkpatrick AAML 126 43 0 25 May 2022
Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models Kushal Tirumala Aram H. Markosyan Luke Zettlemoyer Armen Aghajanyan TDI 127 197 0 22 May 2022
How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing Samuel Sousa Roman Kern PILM AILaw 79 46 0 20 May 2022
FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data Mike He Zhu Léna Néhale Ezzine Dianbo Liu Yoshua Bengio OOD FedML 58 5 0 19 May 2022
Recovering Private Text in Federated Learning of Language Models Samyak Gupta Yangsibo Huang Zexuan Zhong Tianyu Gao Kai Li Danqi Chen FedML 117 80 0 17 May 2022
l-Leaks: Membership Inference Attacks with Logits Shuhao Li Yajie Wang Yuan-zhang Li Yu-an Tan MIACV MIALM 118 3 0 13 May 2022
How to Combine Membership-Inference Attacks on Multiple Updated Models Matthew Jagielski Stanley Wu Alina Oprea Jonathan R. Ullman Roxana Geambasu 87 10 0 12 May 2022
Large Scale Transfer Learning for Differentially Private Image Classification Harsh Mehta Abhradeep Thakurta Alexey Kurakin Ashok Cutkosky 85 41 0 06 May 2022
Provably Confidential Language Modelling Xuandong Zhao Lei Li Yu Wang MU 102 17 0 04 May 2022