arXiv Machine Learning August 19, 2026 By Youwei Zhong, Ben Merbaum, Timos Antonopoulos, Ning Luo, Charalampos Papamanthou, Katerina Sotiraki, Ruzica Piskac

Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees

Read the original on arXiv Machine Learning →

arXiv:2608. 17070v1 Announce Type: new Abstract: With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly important in safety-critical and legal-compliance settings.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 7

Privacy-Preserving Robustness Verification for Neural Networks

arXiv:2607. 05251v1 Announce Type: cross Abstract: Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual property constraints.

By Nianyun Song, Xiaokun Luan, Yu Guo, Rongfang Bie, Meng Sun, Xiyue Zhang

safety

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.

By Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris, Jo\~ao Marques-Silva

benchmarks safety

arXiv Machine Learning

Jul 8

Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates

arXiv:2604. 04738v2 Announce Type: replace-cross Abstract: Fine-tuning is the dominant paradigm for adapting large machine learning models, yet current deployment pipelines provide no way to verify how a released model was updated.

By Zhenhang Shang, Yingzhe Yu, Kani Chen

llms fine-tuning efficiency benchmarks

arXiv Machine Learning

Jul 7

Lipschitz-Based Robustness Certification Under Floating-Point Execution

arXiv:2603. 13334v4 Announce Type: replace Abstract: Lipschitz-based robustness certification bounds a network's sensitivity through concrete numerical computation rather than symbolic reasoning, and so scales efficiently.

By Toby Murray

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.

By Matteo Melis, Jesus Martinez Del Rincon, Vishal Sharma

efficiency benchmarks safety

arXiv AI

Jun 29

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.

By Andrew C. Cullen, Paul Montague, Benjamin I. P. Rubinstein

safety

Related stories

Privacy-Preserving Robustness Verification for Neural Networks

Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications

Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates

Lipschitz-Based Robustness Certification Under Floating-Point Execution

Improving Certified Robustness via Adversarial Distillation

Halt Fast! Early Stopping for Certified Robustness