Protecting Sensitive Data in Image Synthesis via PAC-Private Adaptation for Diffusion Models
cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- SIMD-PAC-DB: Pretty Performant PAC Privacy
- Differentially Private Diffusion Models
- PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
- An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
- Differentially Private Diffusion Models Generate Useful Synthetic Images
- Classifier-Free Diffusion Guidance
- LoRA: Low-Rank Adaptation of Large Language Models
- RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Efficient Differentially Private Fine-Tuning of Diffusion Models
- PAC-Private Autoregressive Generation: Calibrating Noise to Ensemble Disagreement
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- DINOv2: Learning Robust Visual Features without Supervision
- Denoising Diffusion Implicit Models
- A Reproducible Extraction of Training Images from Diffusion Models
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks