vas-group-imperial / venus
Venus is a state-of-the-art sound and complete verification toolkit for Relu-based feed-forward neural networks. It can be used to check reachability and local adversarial robustness properties. Venus implements a MILP-based verification method whereby it leverages dependency relations between the ReLU nodes to prune the search tree that nee…
☆13Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for venus
- OVAL framework for BaB-based Neural Network Verification☆13Updated 9 months ago
- VNN Neural Network Verification Competition 2021☆37Updated 3 years ago
- PLANET: a Piece-wise LineAr feed-forward NEural network verification Tool☆43Updated 5 years ago
- Neural Network Enumeration Tool☆34Updated last year
- The released code of Neurify in NIPS 2018☆46Updated last year
- All code for the Piecewise Linear Neural Networks verification: A comparative study paper☆34Updated 6 years ago
- ☆12Updated last year
- Safety Verification of Deep Neural Networks☆50Updated 6 years ago
- Fourth edition of VNN COMP (2023)☆16Updated last year
- ☆17Updated 2 years ago
- The released code of ReluVal in USENIX Security 2018☆56Updated 4 years ago
- CROWN: A Neural Network Robustness Certification Algorithm for General Activation Functions (This repository is outdated; use https://git…☆16Updated 5 years ago
- Reference implementations for RecurJac, CROWN, FastLin and FastLip (Neural Network verification and robustness certification algorithms)…☆26Updated 5 years ago
- Benchmarks for the VNN Comp 2022☆9Updated 5 months ago
- ☆101Updated 4 years ago
- β-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Verification☆30Updated 3 years ago
- The official repo for GCP-CROWN paper☆12Updated 2 years ago
- ☆26Updated last year
- Neural Network Verification Software Tool☆114Updated last month
- CROWN: A Neural Network Verification Framework for Networks with General Activation Functions☆38Updated 5 years ago
- Efficient Robustness Verification for ReLU networks (this repository is outdated, don't use; checkout our new implementation at https://g…☆30Updated 5 years ago
- Documentation and scripts related to the .nnet file format. This file format specifies a simple text file to define feed-forward, fully-c…☆40Updated last year
- A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]☆88Updated last year
- A Framework for Deep Neural Network Verification☆56Updated 9 months ago
- A method for training neural networks that are provably robust to adversarial attacks. [IJCAI 2019]☆10Updated 5 years ago
- Keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on popular da…☆17Updated 5 months ago
- Sherlock is a tool for output range anaylsis of Deep Neural Networks with ReLU activation units.☆27Updated 4 years ago
- ☆21Updated 2 years ago
- Evaluating Robustness of Neural Networks with Mixed Integer Programming☆113Updated 3 months ago
- Certified defense to adversarial examples using CROWN and IBP. Also includes GPU implementation of CROWN verification algorithm (in PyTor…☆93Updated 3 years ago