eth-sri / deepg
Certifying Geometric Robustness of Neural Networks
☆16Updated 2 years ago
Alternatives and similar repositories for deepg:
Users that are interested in deepg are comparing it to the libraries listed below
- Efficient Robustness Verification for ReLU networks (this repository is outdated, don't use; checkout our new implementation at https://g…☆30Updated 5 years ago
- Benchmark for LP-relaxed robustness verification of ReLU-networks☆41Updated 5 years ago
- The official repo for GCP-CROWN paper☆13Updated 2 years ago
- CROWN: A Neural Network Verification Framework for Networks with General Activation Functions☆38Updated 6 years ago
- Interval attacks (adversarial ML)☆21Updated 5 years ago
- CROWN: A Neural Network Robustness Certification Algorithm for General Activation Functions (This repository is outdated; use https://git…☆16Updated 6 years ago
- Certified defense to adversarial examples using CROWN and IBP. Also includes GPU implementation of CROWN verification algorithm (in PyTor…☆92Updated 3 years ago
- ☆26Updated 2 years ago
- Code for paper "Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers"☆17Updated 2 years ago
- Code for Stability Training with Noise (STN)☆21Updated 4 years ago
- Reference implementations for RecurJac, CROWN, FastLin and FastLip (Neural Network verification and robustness certification algorithms)…☆26Updated 5 years ago
- All code for the Piecewise Linear Neural Networks verification: A comparative study paper☆36Updated 6 years ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆47Updated 2 years ago
- Code release for the ICML 2019 paper "Are generative classifiers more robust to adversarial attacks?"☆23Updated 5 years ago
- VNN Neural Network Verification Competition 2021☆36Updated 3 years ago
- Logit Pairing Methods Can Fool Gradient-Based Attacks [NeurIPS 2018 Workshop on Security in Machine Learning]☆19Updated 6 years ago
- Fourth edition of VNN COMP (2023)☆16Updated last year
- Code for the paper "Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation" by Alexander Levine and Soheil Feizi.☆10Updated 2 years ago
- Learning perturbation sets for robust machine learning☆64Updated 3 years ago
- OVAL framework for BaB-based Neural Network Verification☆13Updated last year
- This repository contains a simple implementation of Interval Bound Propagation (IBP) using TensorFlow: https://arxiv.org/abs/1810.12715☆158Updated 5 years ago
- [ICLR 2020] Code for paper "Robustness Verification for Transformers"☆27Updated 4 months ago
- ☆22Updated 3 years ago
- A powerful white-box adversarial attack that exploits knowledge about the geometry of neural networks to find minimal adversarial perturb…☆12Updated 4 years ago
- An Algorithm to Quantify Robustness of Recurrent Neural Networks☆47Updated 4 years ago
- Official implementation for Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds (NeurIPS, 2021).☆23Updated 2 years ago
- Analysis of Adversarial Logit Pairing☆60Updated 6 years ago
- Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks [NeurIPS 2019]☆50Updated 4 years ago
- Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]☆32Updated 4 years ago
- β-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Verification☆29Updated 3 years ago