Privacy in ML

ICLR 2024arXiv:2310.17884

#2

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Niloofar Mireshghallah, Hyunwoo Kim, Xuhui Zhou et al.

166

ICLR 2024arXiv:2309.17410

#3

Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

Vaidehi Ramesh Patil, Peter Hase, Mohit Bansal

154

ICLR 2024arXiv:2309.11765

#4

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Xinyu Tang, Richard Shin, Huseyin Inan et al.

94

ICLR 2024arXiv:2312.03724

#5

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer

Junyuan Hong, Jiachen (Tianhao) Wang, Chenhui Zhang et al.

62

ECCV 2024arXiv:2403.07362

#6

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

Chongyu Fan, Jiancheng Liu, Alfred Hero et al.

51

ICLR 2024arXiv:2305.01639

#7

Privacy-Preserving In-Context Learning for Large Language Models

Tong Wu, Ashwinee Panda, Jiachen (Tianhao) Wang et al.

51

ICLR 2024arXiv:2302.03098

#8

One-shot Empirical Privacy Estimation for Federated Learning

Galen Andrew, Peter Kairouz, Sewoong Oh et al.

46

ECCV 2024arXiv:2401.06187

#9

Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks

Jing Wu, Mehrtash Harandi

39

ICLR 2024arXiv:2403.00871

#10

Teach LLMs to Phish: Stealing Private Information from Language Models

Ashwinee Panda, Christopher Choquette-Choo, Zhengming Zhang et al.

38

ICML 2024arXiv:2402.13659

#11

Privacy-Preserving Instructions for Aligning Large Language Models

Da Yu, Peter Kairouz, Sewoong Oh et al.

privacy-preserving alignmentsynthetic instruction generationdifferential privacylarge language models+3

36

ICLR 2025arXiv:2410.08109

#12

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

35

CVPR 2024arXiv:2403.12457

#13

Privacy-Preserving Face Recognition Using Trainable Feature Subtraction

Yuxi Mi, Zhizhou Zhong, Yuge Huang et al.

33

ICML 2024arXiv:2310.09130

#14

Split-and-Denoise: Protect large language model inference with local differential privacy

Peihua Mai, Ran Yan, Zhe Huang et al.

local differential privacyprivacy-preserving inferencetext embeddingsembedding-as-a-service+3

32

ICML 2024arXiv:2404.00473

#15

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models

Shanglun Feng, Florian Tramer

privacy backdoorssupply chain attacksmodel tamperingdata reconstruction attacks+3

30

ICML 2024arXiv:2406.02958

#16

PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs

Charlie Hou, Akshat Shrivastava, Hongyuan Zhan et al.

differentially private datasynthetic data generationfederated learningon-device training+2

26

AAAI 2024arXiv:2312.06989

#17

Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks

Caridad Arroyo Arevalo, Sayedeh Leila Noorbakhsh, Yun Dong et al.

25

AAAI 2024arXiv:2303.13269

#18

Disguise without Disruption: Utility-Preserving Face De-identification

Zikui Cai, Zhongpai Gao, Benjamin Planche et al.

24

ICLR 2025arXiv:2402.13846

#19

Language Models are Advanced Anonymizers

Robin Staab, Mark Vero, Mislav Balunovic et al.

23

ICLR 2024arXiv:2310.06549

#20

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks

Lukas Struppek, Dominik Hintersdorf, Kristian Kersting

22

ICLR 2025arXiv:2503.06808

#21

Privacy Auditing of Large Language Models

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

22

ICML 2024arXiv:2310.09639

#22

DPZero: Private Fine-Tuning of Language Models without Backpropagation

Liang Zhang, Bingcong Li, Kiran Thekumparampil et al.

differentially private optimizationzeroth-order methodslanguage model fine-tuningmemory-efficient training+2

22

ICLR 2025arXiv:2410.02486

#23

Encryption-Friendly LLM Architecture

Donghwan Rho, Taeseong Kim, Minje Park et al.

20

ICML 2024arXiv:2404.04500

#24

Trustless Audits without Revealing Data or Models

Suppakit Waiwitlikhit, Ion Stoica, Yi Sun et al.

zero-knowledge proofcryptographic commitmentsalgorithmic transparencytrustless audits+3

19

ICML 2024arXiv:2402.12572

#25

FairProof : Confidential and Certifiable Fairness for Neural Networks

Chhavi Yadav, Amrita Roy Chowdhury, Dan Boneh et al.

zero-knowledge proofsfairness certificationneural networksmodel confidentiality+2

19

ICML 2024arXiv:2306.08842

#26

ViP: A Differentially Private Foundation Model for Computer Vision

Yaodong Yu, Maziar Sanjabi, Yi Ma et al.

differential privacyfoundation modelsself-supervised learningmasked autoencoders+3

ICML 2024arXiv:2405.01031

#27

The Privacy Power of Correlated Noise in Decentralized Learning

Youssef Allouah, Anastasiia Koloskova, Aymane Firdoussi et al.

decentralized learningdifferential privacycorrelated noisesecure communication+4

ICML 2024arXiv:2408.00929

#28

Verification of Machine Unlearning is Fragile

Binchi Zhang, Zihan Chen, Cong Shen et al.

machine unlearningprivacy verificationadversarial unlearningdata removal+3

ICLR 2024arXiv:2310.15526

#29

Privacy Amplification for Matrix Mechanisms

Christopher Choquette-Choo, Arun Ganesh, Thomas Steinke et al.

ICLR 2025arXiv:2405.14457

#30

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

Tudor Cebere, Aurélien Bellet, Nicolas Papernot

17

ICLR 2024arXiv:2309.17310

#31

Leave-one-out Distinguishability in Machine Learning

Jiayuan Ye, Anastasia Borovykh, Soufiane Hayou et al.

17

ICLR 2024arXiv:2302.13945

#32

On Differentially Private Federated Linear Contextual Bandits

Xingyu Zhou, Sayak Ray Chowdhury

16

ICLR 2024arXiv:2404.09816

#33

FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity

Kai Yi, Nidham Gazagnadou, Peter Richtarik et al.

15

ICLR 2024arXiv:2310.16960

#34

Privately Aligning Language Models with Reinforcement Learning

Fan Wu, Huseyin Inan, Arturs Backurs et al.

14

NEURIPS 2025arXiv:2506.04245

#35

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

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

CVPR 2024arXiv:2405.05588

#36

Model Inversion Robustness: Can Transfer Learning Help?

Sy-Tuyen Ho, Koh Jun Hao, Keshigeyan Chandrasegaran et al.

ICLR 2024arXiv:2305.12723

#37

Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting

xinlu zhang, Shiyang Li, Xianjun Yang et al.

ICLR 2025arXiv:2410.06186

#38

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

Milad Nasr, Thomas Steinke, Borja Balle et al.

CVPR 2024arXiv:2404.00777

#39

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

Jhon Lopez, Carlos Hinojosa, Henry Arguello et al.

AAAI 2025arXiv:2408.17354

#40

Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage

Md Rafi Ur Rashid, Jing Liu, Toshiaki Koike-Akino et al.

ICLR 2025arXiv:2410.09591

#41

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy

Yangsibo Huang, Daogao Liu, Lynn Chua et al.

NEURIPS 2025arXiv:2409.09778

#42

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

Siqiao Mu, Diego Klabjan

ICML 2025arXiv:2501.18914

#43

Scaling Laws for Differentially Private Language Models

Ryan McKenna, Yangsibo Huang, Amer Sinha et al.

AAAI 2024arXiv:2312.14388

#44

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

ICML 2025arXiv:2506.06985

#45

Certified Unlearning for Neural Networks

Anastasiia Koloskova, Youssef Allouah, Animesh Jha et al.

ICML 2024arXiv:2201.00292

#46

Fair Data Representation for Machine Learning at the Pareto Frontier

Shizhou Xu, Thomas Strohmer

fair data representationoptimal affine transportwasserstein barycenter characterizationstatistical disparity+4

ICLR 2025arXiv:2412.09119

#47

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

Youssef Allouah, Joshua Kazdan, Rachid Guerraoui et al.

ICLR 2024arXiv:2306.03013

#48

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning

Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanović et al.

ICML 2024arXiv:2403.00278

#49

Shifted Interpolation for Differential Privacy

Jinho Bok, Weijie Su, Jason Altschuler

differential privacyprivacy amplificationnoisy gradient descentf-differential privacy+3

AAAI 2025arXiv:2402.11989

#50

Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models

Zihao Luo, Xilie Xu, Feng Liu et al.

ICLR 2024arXiv:2311.18460

#51

Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework

Maresa Schröder, Dennis Frauen, Stefan Feuerriegel

AAAI 2024arXiv:2312.05551

#52

Multi-Dimensional Fair Federated Learning

Cong Su, Guoxian Yu, Jun Wang et al.

federated learninggroup fairnessclient fairnessdifferential multipliers+3

ICLR 2025arXiv:2406.07687

#53

Adversarial Machine Unlearning

Zonglin Di, Sixie Yu, Yevgeniy Vorobeychik et al.

machine unlearningmembership inference attacksprivacy threatadversarial approach+3

ICML 2024arXiv:2407.09690

#54

Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses

Changyu Gao, Andrew Lowy, Xingyu Zhou et al.

federated learningdifferential privacyheterogeneous dataconvex losses+4

ICML 2024arXiv:2303.08516

#55

Fair Off-Policy Learning from Observational Data

Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel

fair off-policy learningalgorithmic decision-makingobservational datafairness notions+4

AAAI 2024arXiv:2312.08898

#56

Detection and Defense of Unlearnable Examples

Yifan Zhu, lijia Yu, Xiao-Shan Gao

ICML 2024arXiv:2312.06658

#57

Mean Estimation in the Add-Remove Model of Differential Privacy

Alex Kulesza, Ananda Suresh, Yuyan Wang

differential privacyadd-remove modelswap modelmean estimation+3

ICML 2025arXiv:2503.12347

#58

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

Bowen Tan, Zheng Xu, Eric Xing et al.

ICML 2024arXiv:2402.09403

#59

Auditing Private Prediction

Karan Chadha, Matthew Jagielski, Nicolas Papernot et al.

differential privacyprivate predictionprivacy leakage auditingrenyi differential privacy+4

ICML 2024arXiv:2402.10001

#60

Privacy Attacks in Decentralized Learning

Abdellah El Mrini, Edwige Cyffers, Aurélien Bellet

decentralized gradient descentprivacy attacksgossip averaging protocolreconstruction attack+2

ICML 2024arXiv:2405.04034

#61

Differentially Private Post-Processing for Fair Regression

Ruicheng Xian, Qiaobo Li, Gautam Kamath et al.

differential privacyfair regressionstatistical paritypost-processing algorithms+4

ICML 2024arXiv:2402.07471

#62

Differentially Private Decentralized Learning with Random Walks

Edwige Cyffers, Aurélien Bellet, Jalaj Upadhyay

differential privacydecentralized learningrandom walk algorithmspairwise network differential privacy+4

COLM 2025arXiv:2502.17515

#63

Towards User-level Private Reinforcement Learning with Human Feedback

Jiaming Zhang, Mingxi Lei, Meng Ding et al.

Differential PrivacyRLHFLLM alignment

AAAI 2024arXiv:2312.05924

#64

Data-Free Hard-Label Robustness Stealing Attack

Xiaojian Yuan, Kejiang Chen, Wen Huang et al.

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

AAAI 2024arXiv:2401.16687

#65

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

ICLR 2025arXiv:2501.18532

#66

Differentially Private Steering for Large Language Model Alignment

Anmol Goel, Yaxi Hu, Iryna Gurevych et al.

ICLR 2025arXiv:2502.12976

#67

Does Training with Synthetic Data Truly Protect Privacy?

Yunpeng Zhao, Jie Zhang

synthetic data generationprivacy preservationdifferential privacydataset distillation+3

ICLR 2025arXiv:2502.17591

#68

Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility

Martin Kuo, Jingyang Zhang, Jianyi Zhang et al.

ICCV 2025arXiv:2411.15537

#69

MUNBa: Machine Unlearning via Nash Bargaining

Jing Wu, Mehrtash Harandi

machine unlearninggradient conflictnash bargainingimage classification+4

ICML 2024arXiv:2405.08920

#70

Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning

Chendi Wang, Yuqing Zhu, Weijie Su et al.

differential privacyrepresentation learningneural collapsefeature normalization+4

AAAI 2024arXiv:2312.08749

#71

Mitigating Label Bias in Machine Learning: Fairness through Confident Learning

Yixuan Zhang, Boyu Li, Zenan Ling et al.

ICML 2024arXiv:2406.03519

#72

Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning

Saber Malekmohammadi, Yaoliang Yu, YANG CAO

differential privacyfederated learningheterogeneous privacy requirementsnoise level estimation+3

AAAI 2025arXiv:2412.07187

#73

A New Federated Learning Framework Against Gradient Inversion Attacks

Pengxin Guo, Shuang Zeng, Wenhao Chen et al.

federated learninggradient inversion attacksprivacy-preserving methodshypernetwork federated learning+4

ICLR 2024arXiv:2310.03838

#74

Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning

Harsh Chaudhari, Giorgio Severi, Alina Oprea et al.

membership inference attacklabel-only settingdata poisoningprivacy risks+3

ICML 2024arXiv:2306.15056

#75

Optimal Differentially Private Model Training with Public Data

Andrew Lowy, Zeman Li, Tianjian Huang et al.

differential privacylocal differential privacymean estimationempirical risk minimization+3

ICML 2025arXiv:2502.00245

#76

Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion

Tianyuan Zou, Yang Liu, Peng Li et al.

CVPR 2025arXiv:2504.18032

#77

Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models

Chen Chen, Daochang Liu, Mubarak Shah et al.

privacy-utility trade-offdiffusion modelsmemorization mitigationtext-to-image generation+3

AAAI 2025arXiv:2409.14747

#78

Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting

Dasol Choi, Dongbin Na

ICML 2025arXiv:2402.07002

#79

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off

Yuecheng Li, Lele Fu, Tong Wang et al.

AAAI 2024arXiv:2312.10380

#80

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

CVPR 2025arXiv:2503.00383

#81

Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems

Song Xia, Yi Yu, Wenhan Yang et al.

ICML 2024arXiv:2403.02506

#82

Differentially Private Representation Learning via Image Captioning

Tom Sander, Yaodong Yu, Maziar Sanjabi et al.

differential privacyrepresentation learningimage captioningmultimodal datasets+2

COLM 2025arXiv:2412.05734

#83

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

Yuzhou Nie, Zhun Wang, Ye Yu et al.

RRL: Recommendation Reverse Learning

Xiaoyu You, Jianwei Xu, Mi Zhang et al.

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

Tianqu Zhuang, Hongyao Yu, Yixiang Qiu et al.

ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression

Kai Yao, Zhaorui Tan, Tiandi Ye et al.

AAAI 2025arXiv:2412.09812

privacy-preserving tuningoffsite-tuninglayerwise compressionreinforcement learning selection+3

NEURIPS 2025arXiv:2410.02777

#87

Secure and Confidential Certificates of Online Fairness

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

ICML 2025arXiv:2505.01874

#88

Towards Trustworthy Federated Learning with Untrusted Participants

Youssef Allouah, Rachid Guerraoui, John Stephan

ICCV 2025arXiv:2406.01355

#89

Differentially Private Fine-Tuning of Diffusion Models

Yu-Lin Tsai, Yizhe Li, Zekai Chen et al.

ICML 2024arXiv:2401.17823

#90

Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent

Konstantin Donhauser, Javier Abad, Neha Hulkund et al.

differentially private data synthesisoptimal transportparticle gradient descentmarginal-based approaches+2

ICML 2025arXiv:2505.05922

#91

Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy

Haoqi Wu, Wei Dai, Wang Li et al.

ICML 2025arXiv:2411.05733

#92

Differential Privacy Under Class Imbalance: Methods and Empirical Insights

Lucas Rosenblatt, Yuliia Lut, Ethan Turok et al.

ICLR 2025arXiv:2501.13904

#93

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

ICML 2025arXiv:2506.06486

#94

A Certified Unlearning Approach without Access to Source Data

Umit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury et al.

NEURIPS 2025arXiv:2506.12241

#95

Privacy Reasoning in Ambiguous Contexts

Ren Yi, Octavian Suciu, Adrian Gascon et al.

ICML 2024arXiv:2406.15305

#96

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

Ang Li, Yichuan Mo, Mingjie Li et al.

latent diffusion modelsfew-shot fine-tuningdata protectionprivacy preservation+3

CVPR 2024arXiv:2403.04149

#97

MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection

Boyang Peng, Sanqing Qu, Yong Wu et al.

CVPR 2025arXiv:2503.10350

#98

Differentially Private Federated Learning with Time-Adaptive Privacy Spending

Shahrzad Kianidehkordi, Nupur Kulkarni, Adam Dziedzic et al.

Enhancing Facial Privacy Protection via Weakening Diffusion Purification

Ali Salar, Qing Liu, Yingli Tian et al.

ICML 2024arXiv:2402.05453

#100

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Zhenlong Liu, Lei Feng, HUIPING ZHUANG et al.

membership inference attacksprivacy risk mitigationconvex-concave lossloss variance optimization+2