StraightDP: Geometry-Aware Differential Privacy for Rectified-Flow Transformers
Xujun Che, Depeng Xu, Xintao Wu
cs.LG, cs.CR, cs.CV
Submitted: 2026-07-31
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Deep Learning for Classical Japanese Literature
- Unlocking High-Accuracy Differentially Private Image Classification through Scale
- Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions
- Dynamic Differential-Privacy Preserving SGD
- Differentially Private Diffusion Models Generate Useful Synthetic Images
- Toward Training at ImageNet Scale with Differential Privacy
- Rectified Flow: A Marginal Preserving Approach to Optimal Transport
- Large Scale Transfer Learning for Differentially Private Image Classification
- R'enyi Differential Privacy of the Sampled Gaussian Mechanism
- AdaCliP: Adaptive Clipping for Private SGD
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Differentially Private Generative Adversarial Network
- Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks