A Data-Interventional Framework for Auditing Privacy and Fairness in Generative Medical Imaging
cs.CV
Submitted: 2026-09-22
Updated: 2026-09-22
Code: https://github.com/MischaD/Privacy
Terminology
Sources
- Differentially Private Diffusion Models
- Generative Data Mining with Longtail-Guided Diffusion
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
- LCMem: A Universal Model for Robust Image Memorization Detection
- Differentially Private Diffusion Models Generate Useful Synthetic Images
- Towards Black-Box Membership Inference Attack for Diffusion Models
- Efficient Differentially Private Fine-Tuning of Diffusion Models
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Auto-Encoding Variational Bayes
- Scalable Extraction of Training Data from (Production) Language Models
- LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
- Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
- White-box Membership Inference Attacks against Diffusion Models
- Denoising Diffusion Implicit Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models
- Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators
- Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization
- Differentially Private Generative Adversarial Network
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models