Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning

11 January 2021

Papers citing "Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning"

50 / 151 papers shown

Title
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 Gökhan Tür Premkumar Natarajan 39 82 0 02 Aug 2022
Scaling Private Deep Learning with Low-Rank and Sparse Gradients Ryuichi Ito Seng Pei Liew Tsubasa Takahashi Yuya Sasaki Makoto Onizuka 28 1 0 06 Jul 2022
Conflicting Interactions Among Protection Mechanisms for Machine Learning Models S. Szyller Nadarajah Asokan AAML 15 7 0 05 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 40 102 0 30 Jun 2022
Measuring Lower Bounds of Local Differential Privacy via Adversary Instantiations in Federated Learning Marin Matsumoto Tsubasa Takahashi Seng Pei Liew M. Oguchi FedML BDL 15 0 0 18 Jun 2022
Disparate Impact in Differential Privacy from Gradient Misalignment Maria S. Esipova Atiyeh Ashari Ghomi Yaqiao Luo Jesse C. Cresswell 13 25 0 15 Jun 2022
A Survey on Gradient Inversion: Attacks, Defenses and Future Directions Rui Zhang Song Guo Junxiao Wang Xin Xie Dacheng Tao 27 36 0 15 Jun 2022
Bayesian Estimation of Differential Privacy Santiago Zanella Béguelin Lukas Wutschitz Shruti Tople A. Salem Victor Rühle Andrew J. Paverd Mohammad Naseri Boris Köpf Daniel Jones 4 36 0 10 Jun 2022
Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent Da Yu Gautam Kamath Janardhan Kulkarni Tie-Yan Liu Jian Yin Huishuai Zhang 11 17 0 06 Jun 2022
Privacy for Free: How does Dataset Condensation Help Privacy? Tian Dong Bo-Lu Zhao Lingjuan Lyu DD 20 113 0 01 Jun 2022
l-Leaks: Membership Inference Attacks with Logits Shuhao Li Yajie Wang Yuan-zhang Li Yu-an Tan MIACV MIALM 12 2 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 19 10 0 12 May 2022
LPGNet: Link Private Graph Networks for Node Classification Aashish Kolluri Teodora Baluta Bryan Hooi Prateek Saxena 27 24 0 06 May 2022
Unlocking High-Accuracy Differentially Private Image Classification through Scale Soham De Leonard Berrada Jamie Hayes Samuel L. Smith Borja Balle 28 217 0 28 Apr 2022
Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms Saeed Mahloujifar Alexandre Sablayrolles Graham Cormode S. Jha 14 22 0 12 Apr 2022
Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets Florian Tramèr Reza Shokri Ayrton San Joaquin Hoang Minh Le Matthew Jagielski Sanghyun Hong Nicholas Carlini MIACV 25 106 0 31 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 30 151 0 08 Mar 2022
GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation Sina Sajadmanesh Ali Shahin Shamsabadi A. Bellet D. Gática-Pérez 22 63 0 02 Mar 2022
Bounding Membership Inference Anvith Thudi Ilia Shumailov Franziska Boenisch Nicolas Papernot 25 18 0 24 Feb 2022
Debugging Differential Privacy: A Case Study for Privacy Auditing Florian Tramèr Andreas Terzis Thomas Steinke Shuang Song Matthew Jagielski Nicholas Carlini 9 42 0 24 Feb 2022
Differentially Private Speaker Anonymization Ali Shahin Shamsabadi B. M. L. Srivastava A. Bellet Nathalie Vauquier Emmanuel Vincent Mohamed Maouche Marc Tommasi Nicolas Papernot MIACV 38 32 0 23 Feb 2022
Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees Franziska Boenisch Christopher Muhl Roy Rinberg Jannis Ihrig Adam Dziedzic 17 18 0 21 Feb 2022
Trusted AI in Multi-agent Systems: An Overview of Privacy and Security for Distributed Learning Chuan Ma Jun Li Kang Wei Bo Liu Ming Ding Long Yuan Zhu Han H. Vincent Poor 47 42 0 18 Feb 2022
Quantifying Memorization Across Neural Language Models Nicholas Carlini Daphne Ippolito Matthew Jagielski Katherine Lee Florian Tramèr Chiyuan Zhang PILM 14 579 0 15 Feb 2022
What Does it Mean for a Language Model to Preserve Privacy? Hannah Brown Katherine Lee Fatemehsadat Mireshghallah Reza Shokri Florian Tramèr PILM 26 232 0 11 Feb 2022
Privacy-preserving Generative Framework Against Membership Inference Attacks Ruikang Yang Jianfeng Ma Yinbin Miao Xindi Ma 17 5 0 11 Feb 2022
Understanding Rare Spurious Correlations in Neural Networks Yao-Yuan Yang Chi-Ning Chou Kamalika Chaudhuri AAML 16 25 0 10 Feb 2022
Reconstructing Training Data with Informed Adversaries Borja Balle Giovanni Cherubin Jamie Hayes MIACV AAML 30 158 0 13 Jan 2022
Submix: Practical Private Prediction for Large-Scale Language Models Antonio A. Ginart L. V. D. van der Maaten James Y. Zou Chuan Guo 20 22 0 04 Jan 2022
Counterfactual Memorization in Neural Language Models Chiyuan Zhang Daphne Ippolito Katherine Lee Matthew Jagielski Florian Tramèr Nicholas Carlini 24 128 0 24 Dec 2021
Membership Inference Attacks From First Principles Nicholas Carlini Steve Chien Milad Nasr Shuang Song Andreas Terzis Florian Tramèr MIACV MIALM 22 639 0 07 Dec 2021
Decentralized Federated Learning through Proxy Model Sharing Shivam Kalra Junfeng Wen Jesse C. Cresswell M. Volkovs Hamid R. Tizhoosh FedML 11 91 0 22 Nov 2021
Enhanced Membership Inference Attacks against Machine Learning Models Jiayuan Ye Aadyaa Maddi S. K. Murakonda Vincent Bindschaedler Reza Shokri MIALM MIACV 19 231 0 18 Nov 2021
On the Importance of Difficulty Calibration in Membership Inference Attacks Lauren Watson Chuan Guo Graham Cormode Alex Sablayrolles 15 118 0 15 Nov 2021
Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture Xinyu Tang Saeed Mahloujifar Liwei Song Virat Shejwalkar Milad Nasr Amir Houmansadr Prateek Mittal 11 74 0 15 Oct 2021
Generalization Techniques Empirically Outperform Differential Privacy against Membership Inference Jiaxiang Liu Simon Oya Florian Kerschbaum MIACV 6 9 0 11 Oct 2021
Can Stochastic Gradient Langevin Dynamics Provide Differential Privacy for Deep Learning? Guy Heller Ethan Fetaya BDL 17 3 0 11 Oct 2021
SoK: Machine Learning Governance Varun Chandrasekaran Hengrui Jia Anvith Thudi Adelin Travers Mohammad Yaghini Nicolas Papernot 30 16 0 20 Sep 2021
Membership Inference Attacks Against Recommender Systems Minxing Zhang Z. Ren Zihan Wang Pengjie Ren Zhumin Chen Pengfei Hu Yang Zhang MIACV AAML 8 83 0 16 Sep 2021
Statistical Privacy Guarantees of Machine Learning Preprocessing Techniques Ashly Lau Jonathan Passerat-Palmbach 17 1 0 06 Sep 2021
EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning Hongbin Liu Jinyuan Jia Wenjie Qu Neil Zhenqiang Gong 4 94 0 25 Aug 2021
PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning Seng Pei Liew Tsubasa Takahashi Michihiko Ueno FedML 11 29 0 08 Jun 2021
Antipodes of Label Differential Privacy: PATE and ALIBI Mani Malek Ilya Mironov Karthik Prasad I. Shilov Florian Tramèr 8 62 0 07 Jun 2021
Membership Inference Attacks on Machine Learning: A Survey Hongsheng Hu Z. Salcic Lichao Sun Gillian Dobbie Philip S. Yu Xuyun Zhang MIACV 30 412 0 14 Mar 2021
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation Peter Kairouz Ziyu Liu Thomas Steinke FedML 16 232 0 12 Feb 2021
Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent R. Chourasia Jiayuan Ye Reza Shokri FedML 14 69 0 11 Feb 2021
Quantifying and Mitigating Privacy Risks of Contrastive Learning Xinlei He Yang Zhang 11 51 0 08 Feb 2021
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models Yugeng Liu Rui Wen Xinlei He A. Salem Zhikun Zhang Michael Backes Emiliano De Cristofaro Mario Fritz Yang Zhang AAML 15 125 0 04 Feb 2021
Investigating Membership Inference Attacks under Data Dependencies Thomas Humphries Simon Oya Lindsey Tulloch Matthew Rafuse I. Goldberg Urs Hengartner Florian Kerschbaum MIACV MIALM 17 35 0 23 Oct 2020
MACE: A Flexible Framework for Membership Privacy Estimation in Generative Models Yixi Xu S. Mukherjee Xiyang Liu Shruti Tople Rahul Dodhia J. L. Ferres MIACV 19 11 0 11 Sep 2020