Neural Network Verification Software Tool
-
Updated
Oct 9, 2024 - MATLAB
Neural Network Verification Software Tool
DPLL(T)-based Verification tool for DNNs
Formal Verification of Neural Feedback Loops (NFLs)
alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, and 2024)
Benchmark for formally verifying ViTs
Characterizing Data Point Vulnerability via Average-Case Robustness, UAI 2024
auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs
An algorithm to calculate the convex hull of ReLU function for neural network verification.
This github repository contains the official code for the paper, "Evolving Robust Neural Architectures to Defend from Adversarial Attacks"
This github repository contains the official code for the papers, "Robustness Assessment for Adversarial Machine Learning: Problems, Solutions and a Survey of Current Neural Networks and Defenses" and "One Pixel Attack for Fooling Deep Neural Networks"
[CCS 2021] TSS: Transformation-specific smoothing for robustness certification
This code base is intended to serve as a starting point for interested researchers or practitioners to extend or apply the robustness verification portion of the author's Master's thesis " GUM-compliant neural-network robustness verification".
certifying robustness of neural network via convex optimization
The official repo for GCP-CROWN paper
[ICLR 2020] Code for paper "Robustness Verification for Transformers"
[NeurIPS 2021] Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples | ⛰️
β-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Verification
Certified defense to adversarial examples using CROWN and IBP. Also includes GPU implementation of CROWN verification algorithm (in PyTorch).
Sampling-based Scalable Quantitative Verification for DNNs
Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms [NeurIPS 2020]
Add a description, image, and links to the robustness-verification topic page so that developers can more easily learn about it.
To associate your repository with the robustness-verification topic, visit your repo's landing page and select "manage topics."