arXiv Machine Learning
Jul 8
Higher-Order Certified Robustness for Regression
arXiv:2607. 05536v1 Announce Type: cross Abstract: Randomized smoothing has emerged as a scalable technique for certifying the adversarial robustness of classifiers.
Halt Fast! Early Stopping for Certified Robustness
arXiv:2606. 27694v1 Announce Type: cross Abstract: Randomized Smoothing (RS) provides rigorous robustness guarantees for neural networks without architectural constraints, yet its adoption is limited by extreme computational costs.
Related stories
arXiv Machine Learning
Aug 19
Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees
PANDA is a scalable system that uses zero‑knowledge proofs to certify the robustness and fairness of neural networks without revealing their private parameters. Built on the CROWN robustness framework, PANDA introduces a novel algorithm for proving linear relaxation bounds on non‑linear activation layers, producing lightweight proofs. The system can generate proofs for networks with over 2.9 million parameters in just five minutes and verify them in ten seconds, scaling polynomially with network size and enabling verification of models four orders of magnitude larger than prior ZKP‑based approaches.
arXiv Machine Learning
Jun 3
RRISE: Robust Radius Inference via a Surrogate Estimator
arXiv:2606. 02876v1 Announce Type: new Abstract: Randomized smoothing (RS) uses a smoothed classifier to provide architecture-agnostic certificates of $\ell_2$ classification robustness, but its dependence on per-input Monte Carlo (MC) sampling undermines its use in real-time systems.
arXiv AI
Sep 16
Dual Randomized Smoothing: Beyond Global Noise Variance
arXiv:2512.01782v4 Announce Type: replace-cross Abstract: Randomized Smoothing (RS) is a prominent technique for certifying the robustness of neural networks against adversarial perturbations. With R...
arXiv AI
Jul 1
Improving Certified Robustness via Adversarial Distillation
arXiv:2606. 31653v1 Announce Type: cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set.
arXiv Machine Learning
Jun 8
Certified Robustness to Data Poisoning in Gradient-Based Training
arXiv:2406. 05670v3 Announce Type: replace Abstract: Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks.
arXiv AI
Jun 24
Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications
arXiv:2606. 23858v1 Announce Type: cross Abstract: A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify.
arXiv AI
Jul 20
AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing
arXiv:2503. 22998v2 Announce Type: replace-cross Abstract: Despite advancements in Graph Neural Networks (GNNs), adaptive attacks continue to challenge their robustness.
arXiv AI
Jun 16
Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability
arXiv:2606. 16883v1 Announce Type: cross Abstract: Generalization is a critical property of data-driven models, particularly deep learning models deployed in safety-critical applications.
arXiv Machine Learning
Jun 9
LARP: Learner-Agnostic Robust Data Prefiltering
arXiv:2506. 20573v4 Announce Type: replace-cross Abstract: Public datasets, crucial for modern machine learning and statistical inference, often contain low-quality or contaminated samples that can harm model performance.
arXiv AI
Jun 2
CEAR: Certified Ensemble Adversarial Robustness in DNNs
arXiv:2606. 01437v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) are highly susceptible to adversarial perturbations, leading to extensive research on robustness for safety-critical applications.
arXiv Machine Learning
Sep 17
Reliable learning in challenging environments
The paper addresses the challenge of creating machine learning learners that can guarantee provably correct predictions in difficult test-time scenarios, such as adversarial attacks and natural distribution shifts. It introduces a reliable learner with optimal theoretical guarantees for these settings and discusses practical implementations. The authors demonstrate strong performance on examples like linear separators under log-concave distributions and smooth boundary classifiers under smooth probability distributions.