Imagen de Portada

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Meng, Jiayang, Huang, Tao, Chen, Hong, Hou, Chen, Zheng, Guolong
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model
por: Meng, Jiayang, et al.
Publicado: (2024)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
por: Meng, Jiayang, et al.
Publicado: (2025)

Observable Channels, Not Just Storage: Evaluating Privacy Leakage in LLM Agent Pipelines
por: Huang, Tao, et al.
Publicado: (2026)

The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning
por: Xiang, Kunlan, et al.
Publicado: (2025)

Sliced Rényi Pufferfish Privacy: Directional Additive Noise Mechanism and Private Learning with Gradient Clipping
por: Zhang, Tao, et al.
Publicado: (2025)

Understanding Deep Gradient Leakage via Inversion Influence Functions
por: Zhang, Haobo, et al.
Publicado: (2023)

Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
por: Huang, Tao, et al.
Publicado: (2024)

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
por: Rashid, Md Rafi Ur, et al.
Publicado: (2023)

SoK: On Gradient Leakage in Federated Learning
por: Du, Jiacheng, et al.
Publicado: (2024)

Enhancing Privacy of Spatiotemporal Federated Learning against Gradient Inversion Attacks
por: Zheng, Lele, et al.
Publicado: (2024)

Secure Distributed Learning for CAVs: Defending Against Gradient Leakage with Leveled Homomorphic Encryption
por: Najjar, Muhammad Ali, et al.
Publicado: (2025)

Building Gradient Bridges: Label Leakage from Restricted Gradient Sharing in Federated Learning
por: Zhang, Rui, et al.
Publicado: (2024)

Gradient Inversion of Federated Diffusion Models
por: Huang, Jiyue, et al.
Publicado: (2024)

Privacy Loss of Noise Perturbation via Concentration Analysis of A Product Measure
por: Liu, Shuainan, et al.
Publicado: (2025)

Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning
por: Fan, Mingyuan, et al.
Publicado: (2022)

Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models
por: Zhang, Boyang, et al.
Publicado: (2025)

Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning
por: Wang, Zhibo, et al.
Publicado: (2024)

PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning
por: Hou, Sizai, et al.
Publicado: (2024)

Towards Quantum-Safe Federated Learning via Homomorphic Encryption: Learning with Gradients
por: Yan, Guangfeng, et al.
Publicado: (2024)

Mjolnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion
por: Liu, Xuan, et al.
Publicado: (2024)

Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage
por: Shao, Hanyin, et al.
Publicado: (2023)

Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Security
por: Wang, Haodi, et al.
Publicado: (2024)

Enhancing Gradient Variance and Differential Privacy in Quantum Federated Learning
por: Phan, Duc-Thien, et al.
Publicado: (2025)

Enhanced Privacy Bound for Shuffle Model with Personalized Privacy
por: Liu, Yixuan, et al.
Publicado: (2024)

Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising
por: Huang, Tao, et al.
Publicado: (2024)

Uncovering Privacy Vulnerabilities through Analytical Gradient Inversion Attacks
por: Eltaras, Tamer Ahmed, et al.
Publicado: (2025)

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
por: Wang, Yidan, et al.
Publicado: (2025)

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
por: Fu, Jie, et al.
Publicado: (2026)

S-Leak: Leakage-Abuse Attack Against Efficient Conjunctive SSE via s-term Leakage
por: Su, Yue, et al.
Publicado: (2025)

Towards Explainable Privacy Preservation in Federated Learning via Shapley Value-Guided Noise Injection
por: Li, Yunbo, et al.
Publicado: (2025)

DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakage
por: Hmida, Firas Ben, et al.
Publicado: (2026)

Random Gradient Masking as a Defensive Measure to Deep Leakage in Federated Learning
por: Kim, Joon, et al.
Publicado: (2024)

Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
por: Cundy, Chris, et al.
Publicado: (2020)

Quantifying Privacy Leakage in Split Inference via Fisher-Approximated Shannon Information Analysis
por: Deng, Ruijun, et al.
Publicado: (2025)

Label Leakage Attacks in Machine Unlearning: A Parameter and Inversion-Based Approach
por: Zheng, Weidong, et al.
Publicado: (2026)

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
por: Ganev, Georgi, et al.
Publicado: (2025)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
por: Şimşekli, Umut, et al.
Publicado: (2024)

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings
por: Fan, Mingyuan, et al.
Publicado: (2025)

Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
por: Greenewald, Kristjan, et al.
Publicado: (2024)

Computing Maximal Per-Record Leakage and Leakage-Distortion Functions for Privacy Mechanisms under Entropy-Constrained Adversaries
por: Wu, Genqiang, et al.
Publicado: (2026)