BerkeleyLearnVerify / VerifAILinks
VerifAI is a software toolkit for the formal design and analysis of systems that include artificial intelligence (AI) and machine learning (ML) components.
☆201Updated 3 weeks ago
Alternatives and similar repositories for VerifAI
Users that are interested in VerifAI are comparing it to the libraries listed below
Sorting:
- A compiler and scenario generator for the Scenic scenario description language.☆346Updated last week
- Python library for working with Metric Temporal Logic (MTL)☆101Updated 2 years ago
- Neural Network Verification Software Tool☆133Updated 2 weeks ago
- A toolbox for worst-case validation of autonomous policies☆36Updated 2 years ago
- Specification-based real-time monitoring library☆67Updated 4 months ago
- ☆38Updated last month
- Evolutionary test case generation for simulation testing of autonomous vehicles.☆29Updated 2 years ago
- The repository hosts the code for the SBFT CPS Tool competition for testing autonomous cars.☆16Updated 11 months ago
- ☆298Updated 2 weeks ago
- alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, 2024, 2025)☆316Updated 9 months ago
- PLANET: a Piece-wise LineAr feed-forward NEural network verification Tool☆43Updated 6 years ago
- The code of our paper "Misbehaviour Prediction for Autonomous Driving Systems", including our improved Udacity simulator☆22Updated 4 years ago
- Repository for the GRAIC synthesis competition☆23Updated last year
- Documentation and scripts related to the .nnet file format. This file format specifies a simple text file to define feed-forward, fully-c…☆40Updated 7 months ago
- A systematic testing tool for automatically detecting erroneous behaviors of DNN-driven vehicles☆81Updated 6 years ago
- Tool for STL specification validation☆20Updated 6 years ago
- ETH Robustness Analyzer for Deep Neural Networks☆343Updated 2 years ago
- Automatic Crash Constructor from Crash Report (A3CR) Demo of constructing simulations from crash reports☆14Updated 2 years ago
- ☆61Updated last year
- Sherlock is a tool for output range anaylsis of Deep Neural Networks with ReLU activation units.☆30Updated 5 years ago
- CROWN: A Neural Network Robustness Certification Algorithm for General Activation Functions (This repository is outdated; use https://git…☆17Updated 6 years ago
- Safety Verification of Deep Neural Networks☆50Updated 7 years ago
- Temporal Logic Extractor☆11Updated 8 years ago
- A Benchmark for Evaluating Autonomous Vehicles in Safety-critical Scenarios☆135Updated last year
- Implementation of Nvidia's DAVE2 NN in Keras, with some enhancements☆25Updated 8 years ago
- Fourth edition of VNN COMP (2023)☆16Updated 2 years ago
- Benchmarks for the VNN Comp 2023☆16Updated last year
- Neural Network Enumeration Tool☆34Updated 2 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
- Modular autonomous driving platform running on the CARLA simulator and real-world vehicles.☆516Updated 2 years ago