Adversarially Robust PAC Learning with Optimal VC Rates
stat.ML, cs.LG, math.ST, stat.TH
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: 35 pages, 2 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses
- Simplifying Adversarially Robust PAC Learning with Tolerance
- On Evaluating Adversarial Robustness
- Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples?
- Defensive Distillation is Not Robust to Adversarial Examples
- MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
- Adversarial Robustness as a Prior for Learned Representations
- An Optimal Agnostic PAC Algorithm
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Majority-of-Three is Optimal
- ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detection
- Intriguing properties of neural networks
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey