Certification-Based Differentially Private Learning
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- On the Opportunities and Risks of Foundation Models
- CaPC Learning: Confidential and Private Collaborative Learning
- The Trade-Offs of Private Prediction
- Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy
- Relaxation-Informed Training of Neural Network Surrogate Models
- Scalable Private Learning with PATE
- Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
- Between Pure and Approximate Differential Privacy
- Individual Privacy Accounting with Gaussian Differential Privacy
- Opacus: User-Friendly Differential Privacy Library in PyTorch
- Individual Fairness Guarantees for Neural Networks
- Robust Explanation Constraints for Neural Networks
- Hyperparameter Tuning with Renyi Differential Privacy
- R'enyi Differential Privacy of the Sampled Gaussian Mechanism
- On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
- Differentially Private Fine-tuning of Language Models
- Large Language Models Can Be Strong Differentially Private Learners
- Differentially Private Synthetic Data via Foundation Model APIs 2: Text
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