BerkeleyLearnVerify / VerifAI
VerifAI is a software toolkit for the formal design and analysis of systems that include artificial intelligence (AI) and machine learning (ML) components.
☆172Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for VerifAI
- A compiler and scenario generator for the Scenic scenario description language.☆285Updated this week
- Neural Network Verification Software Tool☆112Updated last month
- ☆36Updated 4 years ago
- Python library for working with Metric Temporal Logic (MTL)☆93Updated last year
- Specification-based real-time monitoring library☆50Updated 9 months ago
- alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, and 2024)☆236Updated 3 months ago
- PLANET: a Piece-wise LineAr feed-forward NEural network verification Tool☆42Updated 5 years ago
- Fault Injection for Autonomous Vehicles☆9Updated 5 years ago
- Evolutionary test case generation for simulation testing of autonomous vehicles.☆25Updated last year
- CROWN: A Neural Network Robustness Certification Algorithm for General Activation Functions (This repository is outdated; use https://git…☆16Updated 5 years ago
- The repository hosts the code for the SBFT CPS Tool competition for testing autonomous cars.☆15Updated 7 months ago
- Neural Network Enumeration Tool☆34Updated last year
- ☆260Updated 2 weeks ago
- Attacking Vision based Perception in End-to-end Autonomous Driving Models☆31Updated last year
- Runtime Verification of Autonomous Driving Systems in CARLA☆26Updated 4 years ago
- [PLDI 19'] An Inductive Synthesis Framework for Verifiable Reinforcement Learning☆13Updated 4 years ago
- A Benchmark for Evaluating Autonomous Vehicles in Safety-critical Scenarios☆103Updated 8 months ago
- ☆53Updated 5 months ago
- Demo of the TrustworthySearch API☆19Updated 3 years ago
- Fourth edition of VNN COMP (2023)☆16Updated last year
- The repository hosts the code for the SBST CPS Tool competition for testing autonomous cars.☆20Updated 2 years ago
- Sherlock is a tool for output range anaylsis of Deep Neural Networks with ReLU activation units.☆27Updated 4 years ago
- The released code of ReluVal in USENIX Security 2018☆56Updated 4 years ago
- ☆101Updated 4 years ago
- ☆174Updated 4 years ago
- An open-source software package for fuzzing autonomous driving systems in high-fidelity simulators☆30Updated 2 years ago
- Automatic Crash Constructor from Crash Report (A3CR) Demo of constructing simulations from crash reports☆11Updated last year
- Safety Verification of Deep Neural Networks☆50Updated 6 years ago
- A systematic testing tool for automatically detecting erroneous behaviors of DNN-driven vehicles☆79Updated 5 years ago
- Python API for Simulator☆58Updated 2 years ago