Privacy in ML

ICLR 2025arXiv:2410.08109

#2

Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning

Chongyu Fan, Jiancheng Liu, Alfred Hero et al.

A Closer Look at Machine Unlearning for Large Language Models

Xiaojian Yuan, Tianyu Pang, Chao Du et al.

machine unlearninglarge language modelsentropy maximizationanswer preservation loss+4

28

CVPR 2024arXiv:2302.06637

#4

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

Chulin Xie, De-An Huang, Wenda Chu et al.

20

AAAI 2024arXiv:2312.14388

#5

Encryption-Friendly LLM Architecture

Donghwan Rho, Taeseong Kim, Minje Park et al.

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

Tudor Cebere, Aurélien Bellet, Nicolas Papernot

A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility

Chen E, Yang Cao, Ge Yifei

local differential privacyprivacy amplificationshuffle modelpersonalized ldp+3

12

ICLR 2024arXiv:2311.18460

#8

Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework

Maresa Schröder, Dennis Frauen, Stefan Feuerriegel

11

CVPR 2024arXiv:2404.00777

#9

Privacy-Preserving Optics for Enhancing Protection in Face De-Identification

Jhon Lopez, Carlos Hinojosa, Henry Arguello et al.

11

ICLR 2025arXiv:2407.02551

#10

Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions

Siqiao Mu, Diego Klabjan

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy

Yangsibo Huang, Daogao Liu, Lynn Chua et al.

Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses

David Glukhov, Ziwen Han, I Shumailov et al.

information leakagedual-intent queriesinferential adversariessafety-utility trade-off+4

10

AAAI 2024arXiv:2312.05551

#13

Multi-Dimensional Fair Federated Learning

Cong Su, Guoxian Yu, Jun Wang et al.

federated learninggroup fairnessclient fairnessdifferential multipliers+3

9

ICML 2025arXiv:2501.18914

#14

Scaling Laws for Differentially Private Language Models

Ryan McKenna, Yangsibo Huang, Amer Sinha et al.

9

ICML 2025arXiv:2503.12347

#15

Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs

Bowen Tan, Zheng Xu, Eric Xing et al.

9

AAAI 2024arXiv:2312.10380

#16

Differentially Private Steering for Large Language Model Alignment

Anmol Goel, Yaxi Hu, Iryna Gurevych et al.

PPIDSG: A Privacy-Preserving Image Distribution Sharing Scheme with GAN in Federated Learning

Yuting Ma, Yuanzhi Yao, Xiaohua Xu

federated learningprivacy-preserving sharingreconstruction attacksinference attacks+4

7

ICML 2025arXiv:2502.00245

#18

Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion

Tianyuan Zou, Yang Liu, Peng Li et al.

7

AAAI 2024arXiv:2312.05924

#19

Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks

Tianqu Zhuang, Hongyao Yu, Yixiang Qiu et al.

Data-Free Hard-Label Robustness Stealing Attack

Xiaojian Yuan, Kejiang Chen, Wen Huang et al.

model stealing attackshard-label queriesrobustness stealingdata-free attacks+4

6

ICML 2025arXiv:2505.01874

#21

Towards Trustworthy Federated Learning with Untrusted Participants

Youssef Allouah, Rachid Guerraoui, John Stephan

5

ICLR 2025arXiv:2501.13904

#22

Differentially Private Federated Learning with Time-Adaptive Privacy Spending

Shahrzad Kianidehkordi, Nupur Kulkarni, Adam Dziedzic et al.

Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models

Linh Tran, Wei Sun, Stacy Patterson et al.

federated prompt learningmultimodal large language modelsdifferential privacyvision-language models+3

5

ICML 2025arXiv:2411.05733

#24

Differential Privacy Under Class Imbalance: Methods and Empirical Insights

Lucas Rosenblatt, Yuliia Lut, Ethan Turok et al.

4

AAAI 2025arXiv:2406.11087

#25

DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models

Yanming Liu, Xinyue Peng, Yuwei Zhang et al.

3

ECCV 2024arXiv:2408.14738

#26

Language Models are Advanced Anonymizers

Robin Staab, Mark Vero, Mislav Balunovic et al.

Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation

Bochao Liu, Pengju Wang, Shiming Ge

3

NeurIPS 2025arXiv:2506.01420

#28

Self-Refining Language Model Anonymizers via Adversarial Distillation

Kyuyoung Kim, Hyunjun Jeon, Jinwoo Shin

language model anonymizationadversarial distillationprivacy protectionpreference learning+3

3

NeurIPS 2025arXiv:2404.11577

#29

A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation

Yiwen Tu, Pingbang Hu, Jiaqi Ma

machine unlearningmembership inference attackcryptographic gamedata removal efficacy+2

AAAI 2025arXiv:2402.02629

#30

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks

Chen Feng, Ziquan Liu, Zhuo Zhi et al.

ICML 2025arXiv:2505.23968

#31

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Stephan Rabanser, Ali Shahin Shamsabadi, Olive Franzese et al.

ICML 2025arXiv:2505.15694

#32

A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO

Xingyu Zhou, Yulian Wu, Francesco Orabona

ICML 2025arXiv:2503.03622

#33

It's My Data Too: Private ML for Datasets with Multi-User Training Examples

Arun Ganesh, Ryan McKenna, Hugh B McMahan et al.

ICML 2025arXiv:2506.05101

#34

Privacy Amplification Through Synthetic Data: Insights from Linear Regression

Clément Pierquin, Aurélien Bellet, Marc Tommasi et al.

ICML 2025arXiv:2502.02410

#35

Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting

Jan Schuchardt, Mina Dalirrooyfard, Jed Guzelkabaagac et al.

ICML 2025arXiv:2503.12314

#36

Empirical Privacy Variance

Yuzheng Hu, Fan Wu, Ruicheng Xian et al.

ICML 2025arXiv:2503.03043

#37

Leveraging Randomness in Model and Data Partitioning for Privacy Amplification

Andy Dong, Wei-Ning Chen, Ayfer Ozgur

ICML 2025arXiv:2505.18786

#38

Leveraging Per-Instance Privacy for Machine Unlearning

Naz Sepahvand, Anvith Thudi, Berivan Isik et al.

AAAI 2024arXiv:2312.08685

#39

Privacy Amplification by Iteration for ADMM with (Strongly) Convex Objective Functions

T-H. Hubert Chan, Hao Xie, Mengshi ZHAO

privacy amplificationadmm variantsconvex optimizationdifferential privacy+4

NeurIPS 2025arXiv:2504.14368

#40

Can Private Machine Learning Be Fair?

Joseph Rance, Filip Svoboda

Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

Shlomi Hod, Lucas Rosenblatt, Julia Stoyanovich

differential privacytabular data synthesisprivacy-utility tradeoffsurrogate public data+3

NeurIPS 2025arXiv:2506.08347

#42

Privacy-Aware Lifelong Learning

Ozan Özdenizci, Elmar Rueckert, Robert Legenstein

Differentially Private Relational Learning with Entity-level Privacy Guarantees

Yinan Huang, Haoteng Yin, Eli Chien et al.

differential privacyrelational learningentity-level privacygradient clipping+4

NeurIPS 2025arXiv:2510.17000

#44

Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning

Marlon Tobaben, Hibiki Ito, Joonas Jälkö et al.

Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery

Shiji Zhou, Tianbai Yu, Zhi Zhang et al.

Online Locally Differentially Private Conformal Prediction via Binary Inquiries

Qiangqiang Zhang, Chenfei Gu, Xinwei Feng et al.

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

Guangchen (Eric) Lan, Huseyin A. Inan, Sahar Abdelnabi et al.

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples

Hsiang Hsu, Pradeep Niroula, Zichang He et al.

Factor Decorrelation Enhanced Data Removal from Deep Predictive Models

Wenhao Yang, Lin Li, Xiaohui Tao et al.

Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs

Masahiro Kaneko, Timothy Baldwin

adversarial attacksinformation-theoretic boundslarge language modelssystem-prompt leakage+4

NeurIPS 2025arXiv:2506.10364

#51

Can We Infer Confidential Properties of Training Data from LLMs?

Pengrun Huang, Chhavi Yadav, Kamalika Chaudhuri et al.

property inference attackslarge language modelsfine-tuning datasetsconfidential data leakage+3

#52

DictPFL: Efficient and Private Federated Learning on Encrypted Gradients

Jiaqi Xue, Mayank Kumar, Yuzhang Shang et al.

How Well Can Differential Privacy Be Audited in One Run?

Amit Keinan, Moshe Shenfeld, Katrina Ligett

Rethinking the Role of Verbatim Memorization in LLM Privacy

Tom Sander, Bargav Jayaraman, Mark Ibrahim et al.

verbatim memorizationprivacy leakagelanguage model fine-tuningpii extraction+4

NeurIPS 2025arXiv:2510.21060

#55

On the Sample Complexity of Differentially Private Policy Optimization

Yi He, Xingyu Zhou

differential privacypolicy optimizationreinforcement learningsample complexity+3

NeurIPS 2025arXiv:2510.23935

#56

Versatile differentially private learning for general loss functions

Qilong Lu, Songxi Chen, Yumou Qiu

Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis

Enze Shi, Pankaj Bhagwat, Zhixian Yang et al.

sufficient dimension reductionfairness-utility trade-offinfluence functionssensitive information removal+3

NeurIPS 2025arXiv:2507.06969

#58

Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy

Bogdan Kulynych, Juan Gomez, Georgios Kaissis et al.

differential privacyhypothesis-testing interpretationprivacy risk quantificationre-identification risk+4

NeurIPS 2025arXiv:2507.09990

#59

Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix

Ming Wen, Jiaqi Zhu, Yuedong Xu et al.

differential privacyfederated learninglow rank adaptationlarge language models+4

NeurIPS 2025arXiv:2511.10859

#60

Private Zeroth-Order Optimization with Public Data

Xuchen Gong, Tian Li

differentially private optimizationzeroth-order methodsgradient approximationprivacy/utility tradeoff+3

#61

Beyond Prediction: Managing the Repercussions of Machine Learning Applications

Aline Weber, Blossom Metevier, Yuriy Brun et al.

Deep Learning with Plausible Deniability

Wenxuan Bao, Shan Jin, Hadi Abdullah et al.

privacy attacksdifferential privacyplausible deniabilitytraining algorithm+2

private data selectionmulti-party computationtransformer modelsdata markets+3

#63

Individual Fairness In Strategic Classification

Zhiqun Zuo, Mohammad Mahdi Khalili

SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation

Xu Ouyang, Felix Xiaozhu Lin, Yangfeng Ji

ICLR 2025

#65

Online robust locally differentially private learning for nonparametric regression

Chenfei Gu, Qiangqiang Zhang, Ting Li et al.

nonparametric regressiononline learningdifferential privacyhuber loss+4

machine unlearningdata attributionforget set removalmodel fine-tuning+3

#66

Differentially private optimization for non-decomposable objective functions

Weiwei Kong, Andres Munoz medina, Mónica Ribero

Machine Unlearning via Simulated Oracle Matching

Kristian G Georgiev, Roy Rinberg, Sam Park et al.

ICLR 2025

ICLR 2025arXiv:2412.09119

#68

The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning

Youssef Allouah, Joshua Kazdan, Rachid Guerraoui et al.

NeurIPS 2025arXiv:2511.01307

#69

Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models

Tae-Young Lee, Juwon Seo, Jong Hwan Ko et al.

privacy protectiondiffusion modelspersonalization techniquesadversarial perturbation+4

NeurIPS 2025arXiv:2510.00574

#70

Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings

Bo Li, Wei Wang, Peng Ye

private online learningadaptive adversarydifferential privacyrealizable setting+4

#71

Private Training Large-scale Models with Efficient DP-SGD

Liangyu Wang, Junxiao Wang, Jie Ren et al.

differential privacydp-sgd optimizationper-sample gradient clippinglarge language models+3

ICLR 2025arXiv:2503.08085

#72

Building Blocks of Differentially Private Training

Mahmoud Hegazy, Aymeric Dieuleveut

PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models

Kyeongkook Seo, Dong-Jun Han, Jaejun Yoo

NeurIPS 2025arXiv:2407.04884

#74

PFGuard: A Generative Framework with Privacy and Fairness Safeguards

Soyeon Kim, Yuji Roh, Geon Heo et al.

Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy

Rob Romijnders, Antti Koskela

ICLR 2025arXiv:2502.12976

#76

Does Training with Synthetic Data Truly Protect Privacy?

Yunpeng Zhao, Jie Zhang

synthetic data generationprivacy preservationdifferential privacydataset distillation+3

NeurIPS 2025arXiv:2510.04027

#77

Multi-Class Support Vector Machine with Differential Privacy

Jinseong Park, Yujin Choi, Jaewook Lee

differential privacysupport vector machinesmulti-class classificationprivacy-preserving models+4

NeurIPS 2025arXiv:2509.08195

#78

BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection

Yihan Wang, Yiwei Lu, Xiao-Shan Gao et al.

Privacy Auditing of Large Language Models

Ashwinee Panda, Xinyu Tang, Christopher Choquette-Choo et al.

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD

Milad Nasr, Thomas Steinke, Borja Balle et al.

Near-Exact Privacy Amplification for Matrix Mechanisms

Christopher Choquette-Choo, Arun Ganesh, Saminul Haque et al.

Sum Estimation under Personalized Local Differential Privacy

Dajun Sun, Wei Dong, Yuan Qiu et al.

Sketched Gaussian Mechanism for Private Federated Learning

Qiaobo Li, Zhijie Chen, Arindam Banerjee

federated learningdifferential privacygradient compressionsketching dimension+3

NeurIPS 2025arXiv:2412.06966

#84

Secure and Confidential Certificates of Online Fairness

Olive Franzese, Ali Shahin Shamsabadi, Carter Luck et al.

Privacy Reasoning in Ambiguous Contexts

Ren Yi, Octavian Suciu, Adrian Gascon et al.

Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks

Jing Wu, Mehrtash Harandi

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen et al.

machine unlearninggenerative ai policyprivacy preservationcopyright removal+3

ICLR 2025arXiv:2406.07687

#88

Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators

Pratyush Maini, Hritik Bansal

Adversarial Machine Unlearning

Zonglin Di, Sixie Yu, Yevgeniy Vorobeychik et al.

machine unlearningmembership inference attacksprivacy threatadversarial approach+3

NeurIPS 2025arXiv:2508.15183

#90

Private Hyperparameter Tuning with Ex-Post Guarantee

Badih Ghazi, Pritish Kamath, Alexander Knop et al.

NeurIPS 2025arXiv:2505.24379

#91

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM

Xiaoyu Wu, Yifei Pang, Terrance Liu et al.

data extraction attacksexact unlearningprivacy risksmodel guidance+2

ICLR 2025arXiv:2504.09330

#92

Online Sensitivity Optimization in Differentially Private Learning

8623 Filippo Galli, Catuscia Palamidessi, Tommaso Cucinotta

Regretful Decisions under Label Noise

Sujay Nagaraj, Yang Liu, Flavio Calmon et al.

label noiseclinical prediction tasksinstance-level impactregret minimization+3

AAAI 2025arXiv:2412.14080

#94

On the Robustness of Distributed Machine Learning Against Transfer Attacks

Sebastien Andreina, Pascal Zimmer, Ghassan Karame

AAAI 2024arXiv:2401.16687

#95

Mitigating Label Bias in Machine Learning: Fairness through Confident Learning

Yixuan Zhang, Boyu Li, Zenan Ling et al.

PrivDNFIS: Privacy-preserving and Efficient Deep Neuro-Fuzzy Inference System

Hao Ren, Xiao Lan, Rui Tang et al.

Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning

Amr Abourayya, Jens Kleesiek, Kanishka Rao et al.

Towards Fairness-Aware Adversarial Learning

Yanghao Zhang, Tianle Zhang, Ronghui Mu et al.

On Probabilistic Truncation in Privacy-preserving Machine Learning

Lijing Zhou, Bingsheng Zhang, Ziyu Wang et al.

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks

Lulu Xue, Shengshan Hu, Ruizhi Zhao et al.

gradient inversion attackscollaborative learningprivacy preservationgradient pruning+2