paper-with-me

Papers

Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising

2024-11-05 · Tao Huang, Jiayang Meng, Hong Chen, Guolong Zheng, Xu Yang, Xun Yi, Hua Wang

We investigate the construction of gradient-guided conditional diffusion models for reconstructing private images, focusing on the adversarial interplay between differential privacy noise and the denoising capabilities of diffusion models. While current gradient-based reconstruction methods struggle with high-resolution images due to computational complexity and prior knowledge requirements, we propose two novel methods that require minimal modifications to the diffusion model's generation process and eliminate the need for prior knowledge. Our approach leverages the strong image generation capabilities of diffusion models to reconstruct private images starting from randomly generated noise, even when a small amount of differentially private noise has been added to the gradients. We also conduct a comprehensive theoretical analysis of the impact of differential privacy noise on the quality of reconstructed images, revealing the relationship among noise magnitude, the architecture of attacked models, and the attacker's reconstruction capability. Additionally, extensive experiments validate the effectiveness of our proposed methods and the accuracy of our theoretical findings, suggesting new directions for privacy risk auditing using conditional diffusion models.

📄 PDF Abstract BibTeX arXiv:2411.03053

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage GenerationImage Reconstruction

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DP-aware AdaLN-Zero: Taming Conditioning-Induced Heavy-Tailed Gradients in Differentially Private Diffusion

2026-02-26 · Tao Huang, Jiayang Meng, Xu Yang, Chen Hou 외 arxiv

Condition injection enables diffusion models to generate context-aware outputs, which is essential for many time-series tasks. However, heterogeneous conditional contexts (e.g., observed history, missingness patterns or …

More Control for Free! Image Synthesis with Semantic Diffusion Guidance

2021-12-10 · Xihui Liu, Dong Huk Park, Samaneh Azadi, Gong Zhang 외

Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from a reference image. Recently, denoising diffusion probabilistic models have been shown to generate more real…

continuous-controlContinuous ControlDenoisingImage Generation

Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model

2024-06-13 · Jiayang Meng, Tao Huang, Hong Chen, Cuiping Li

Gradient leakage has been identified as a potential source of privacy breaches in modern image processing systems, where the adversary can completely reconstruct the training images from leaked gradients. However, existi…

Image ReconstructionmodelReconstruction Attack

RePoseDM: Recurrent Pose Alignment and Gradient Guidance for Pose Guided Image Synthesis

2023-10-24 · Anant Khandelwal

Pose-guided person image synthesis task requires re-rendering a reference image, which should have a photorealistic appearance and flawless pose transfer. Since person images are highly structured, existing approaches re…

Image GenerationPose-Guided Image GenerationPose Transfervalid

Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Sampling

2026-06-11 · Jagriti Singh, Shekhar Verma, Muneendra Ojha arxiv

Diffusion models have emerged as state-of-the-art generative models for high-fidelity image synthesis, particularly in their classifier-free guided and classifier-guided forms. However, standard classifier guidance conce…