Skip to content
Review

Verification of DNNs with Marabou – Abstract

TL;DR

This tutorial explores Marabou, a tool for formally verifying deep neural networks (DNNs), and presents the theoretical foundations of DNN verification and an overview of Marabou’s core algorithms.

View source

Similar papers

#machine learning Preprint Sep 2026

Exploring Solver-Level Warmstarting for Neural Network Verification

This work explores the application of solver-level warmstarting for neural network verification to exploit information from previous solutions, using a pipeline that is generalisable and potentially adaptable to state-of-the-art verifiers.

Annelot W. Bosman, Ming-Hao Liu, Marta Z. Kwiatkowska et al. · 0 citations
#machine learning Preprint Sep 2026

ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models

ZonoGpt, an abstract domain for verifying large transformers that maintains a space complexity independent of network depth, is introduced, an abstract domain for verifying large transformers that maintains a space complexity independent of network depth.

Hai Duong, Thanh Le, Thanhvu Nguyen · 1 citation
#artificial intelligence Review Sep 2026

NNV3: Expanding Neural Network Verification to New Architectures and Domains

NNV3 is presented, the latest version of the Neural Network Verification tool, a MATLAB framework for formal verification of deep learning models and learning-enabled cyber-physical systems, demonstrating NNV's maturation into a comprehensive, robust, and accessible verification tool for a diverse range of AI systems.

Anne M. Tumlin, Samuel Sasaki, Ben Wooding et al. · 0 citations
#artificial intelligence Preprint Aug 2026

HSRM: Hidden-State Reward Models for Test-Time Verification

HSRM is introduced, a lightweight hidden-state reward model that verifies candidate solutions by directly reading the generator's internal representations rather than re-processing its text, providing an efficient alternative to text-only verification by reusing representations already computed during generation.

Xianzhi Li, Xiao-Dan Zhu · 0 citations
#machine learning Preprint Sep 2026

CLAD: Constrained Abstract Domain for Neural Network Verification

Constrained Lagrangian Abstract Domain (CLAD), a new abstract domain that computes a sound over-approximation of neural networks over input regions defined by a combination of convex constraints, is introduced.

Hai Duong, Thanh Le, Thanhvu Nguyen · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.