Image de couverture de livre

Mitigating Membership Inference in Intermediate Representations with Differentially Private Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Meng, Jiayang, Huang, Tao, Hou, Chen, Zheng, Guolong, Chen, Hong
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DP-aware AdaLN-Zero: Taming Conditioning-Induced Heavy-Tailed Gradients in Differentially Private Diffusion
par: Huang, Tao, et autres
Publié: (2026)

Intermediate Outputs Are More Sensitive Than You Think
par: Huang, Tao, et autres
Publié: (2024)

Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weight
par: Huang, Tao, et autres
Publié: (2024)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
par: Meng, Jiayang, et autres
Publié: (2025)

Bayesian Inference of Training Dataset Membership
par: Huang, Yongchao
Publié: (2025)

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
par: Meng, Jiayang, et autres
Publié: (2025)

Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising
par: Huang, Tao, et autres
Publié: (2024)

Range Membership Inference Attacks
par: Tao, Jiashu, et autres
Publié: (2024)

Secure Aggregation is Not Private Against Membership Inference Attacks
par: Ngo, Khac-Hoang, et autres
Publié: (2024)

AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation
par: Chen, Ying, et autres
Publié: (2025)

DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation
par: Gao, Xinyu, et autres
Publié: (2025)

Mitigating Membership Inference Vulnerability in Personalized Federated Learning
par: Jung, Kangsoo, et autres
Publié: (2025)

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
par: Liu, Zhenlong, et autres
Publié: (2024)

Auditing Training Data in Generative Music Models via Black-Box Membership Inference
par: Liu, Yi Chen, et autres
Publié: (2026)

Imitative Membership Inference Attack
par: Du, Yuntao, et autres
Publié: (2025)

Explanations Leak: Membership Inference with Differential Privacy and Active Learning Defense
par: Ezzeddine, Fatima, et autres
Publié: (2026)

MCMC for Bayesian estimation of Differential Privacy from Membership Inference Attacks
par: Yildirim, Ceren, et autres
Publié: (2025)

MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training
par: Li, Jiacheng, et autres
Publié: (2023)

Model Agnostic Differentially Private Causal Inference
par: Lebeda, Christian Janos, et autres
Publié: (2025)

Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference
par: Chen, Depeng, et autres
Publié: (2024)

CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning
par: Chen, Depeng, et autres
Publié: (2024)

Silver Linings in the Shadows: Harnessing Membership Inference for Machine Unlearning
par: Sula, Nexhi, et autres
Publié: (2024)

Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
par: Tran, Toan, et autres
Publié: (2025)

Better Membership Inference Privacy Measurement through Discrepancy
par: Wu, Ruihan, et autres
Publié: (2024)

(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs
par: Tao, Jiashu, et autres
Publié: (2025)

Cascading and Proxy Membership Inference Attacks
par: Du, Yuntao, et autres
Publié: (2025)

Differentially Private Non-convex Distributionally Robust Optimization
par: Xu, Difei, et autres
Publié: (2026)

Nearly Optimal Differentially Private ReLU Regression
par: Ding, Meng, et autres
Publié: (2025)

MRMMIA: Membership Inference Attacks on Memory in Chat Agents
par: Chen, Kai, et autres
Publié: (2026)

Noise-Aware Differentially Private Variational Inference
par: Alrawajfeh, Talal, et autres
Publié: (2024)

Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
par: Zhang, Jiaming, et autres
Publié: (2026)

Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble
par: Wang, Zhiqi, et autres
Publié: (2025)

Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization
par: Xu, Difei, et autres
Publié: (2026)

Statistical Inference for Differentially Private Stochastic Gradient Descent
par: Xia, Xintao, et autres
Publié: (2025)

Differentially Private Distributed Inference
par: Papachristou, Marios, et autres
Publié: (2024)

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
par: Zhang, Chenxiang, et autres
Publié: (2025)

Optimal Differentially Private Model Training with Public Data
par: Lowy, Andrew, et autres
Publié: (2023)

Causal Evaluation of Membership Inference Attacks
par: Even, Mathieu, et autres
Publié: (2026)

Differentially Private Sparse Linear Regression with Heavy-tailed Responses
par: Tian, Xizhi, et autres
Publié: (2025)

Differentially Private Covariate Balancing Causal Inference
par: Ohnishi, Yuki, et autres
Publié: (2024)