eth-sri / dl2Links
DL2 is a framework that allows training neural networks with logical constraints over numerical values in the network (e.g. inputs, outputs, weights) and to query networks for inputs fulfilling a logical formula.
☆86Updated 11 months ago
Alternatives and similar repositories for dl2
Users that are interested in dl2 are comparing it to the libraries listed below
Sorting:
- All code for the Piecewise Linear Neural Networks verification: A comparative study paper☆35Updated 6 years ago
- ☆24Updated 4 years ago
- SyReNN: Symbolic Representations for Neural Networks☆41Updated 2 years ago
- VNN Neural Network Verification Competition 2021☆36Updated 4 years ago
- Certifying Geometric Robustness of Neural Networks☆16Updated 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- Efficient Robustness Verification for ReLU networks (this repository is outdated, don't use; checkout our new implementation at https://g…☆30Updated 5 years ago
- ☆101Updated 5 years ago
- implementation of ICML 2018 paper, Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples☆77Updated 5 years ago
- Safety Verification of Deep Neural Networks☆50Updated 7 years ago
- This repository contains a simple implementation of Interval Bound Propagation (IBP) using TensorFlow: https://arxiv.org/abs/1810.12715☆161Updated 5 years ago
- Learning Certified Individually Fair Representations☆24Updated 4 years ago
- Python package for Sentential Decision Diagrams (SDD)☆63Updated 4 months ago
- Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks [NeurIPS 2019]☆50Updated 5 years ago
- Semantic Loss code☆59Updated 6 years ago
- A curated list of papers related to program synthesis, program induction, program execution, program and code repair, and programmatic re…☆165Updated 3 years ago
- HOUDINI: Lifelong Learning as Program Synthesis☆48Updated 3 months ago
- Code for "Learning Compositional Rules via Neural Program Synthesis"☆60Updated 4 years ago
- ☆46Updated last year
- A certifiable defense against adversarial examples by training neural networks to be provably robust☆221Updated 11 months ago
- Logistic Circuits☆36Updated 6 years ago
- Benchmark for LP-relaxed robustness verification of ReLU-networks☆41Updated 6 years ago
- Sherlock is a tool for output range anaylsis of Deep Neural Networks with ReLU activation units.☆29Updated 5 years ago
- Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis☆38Updated 2 years ago
- ETH Robustness Analyzer for Deep Neural Networks☆339Updated 2 years ago
- CROWN: A Neural Network Verification Framework for Networks with General Activation Functions☆38Updated 6 years ago
- Tensorflow implementation for the Class-wise Selective Rationalization☆14Updated 2 years ago
- Official code for paper: INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving☆39Updated 2 years ago
- ☆17Updated 5 years ago
- Implementation of GNN ReLU branching strategies☆10Updated 4 years ago
- Interview questions for Computer Science faculty jobs☆40Updated last year