IBM / CNN-Cert
Codes for reproducing the experimental results in "CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks", published at AAAI 2019
☆27Updated 3 years ago
Alternatives and similar repositories for CNN-Cert
Users that are interested in CNN-Cert are comparing it to the libraries listed below
Sorting:
- A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]☆89Updated 2 years ago
- This repo keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on …☆99Updated 2 years ago
- AAAI 2019 oral presentation☆50Updated 3 weeks ago
- An Algorithm to Quantify Robustness of Recurrent Neural Networks☆48Updated 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- Efficient Robustness Verification for ReLU networks (this repository is outdated, don't use; checkout our new implementation at https://g…☆30Updated 5 years ago
- ☆26Updated 2 years ago
- Benchmark for LP-relaxed robustness verification of ReLU-networks☆41Updated 6 years ago
- A method for training neural networks that are provably robust to adversarial attacks. [IJCAI 2019]☆10Updated 5 years ago
- Certified defense to adversarial examples using CROWN and IBP. Also includes GPU implementation of CROWN verification algorithm (in PyTor…☆94Updated 3 years ago
- The official repo for GCP-CROWN paper☆13Updated 2 years ago
- A community-run reference for state-of-the-art adversarial example defenses.☆50Updated 7 months ago
- Code for "Robustness May Be at Odds with Accuracy"☆91Updated 2 years ago
- Interval attacks (adversarial ML)☆21Updated 5 years ago
- Official TensorFlow implementation of "Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization" (ICML 2019)☆40Updated 4 years ago
- Convex Layerwise Adversarial Training (COLT)☆28Updated 4 years ago
- Analysis of Adversarial Logit Pairing☆60Updated 6 years ago
- Official implementation for paper: A New Defense Against Adversarial Images: Turning a Weakness into a Strength☆38Updated 5 years ago
- Fastened CROWN: Tightened Neural Network Robustness Certificates☆10Updated 5 years ago
- Fourth edition of VNN COMP (2023)☆16Updated 2 years ago
- Library for training globally-robust neural networks.☆28Updated last year
- Code for "On Adaptive Attacks to Adversarial Example Defenses"☆87Updated 4 years ago
- Code for Stability Training with Noise (STN)☆21Updated 4 years ago
- Code for "Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors"☆64Updated 5 years ago
- [NeurIPS 2021] Fast Certified Robust Training with Short Warmup☆24Updated last year
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆55Updated 3 years ago
- All code for the Piecewise Linear Neural Networks verification: A comparative study paper☆36Updated 6 years ago
- Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs☆97Updated 4 years ago
- Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.☆49Updated 5 years ago
- ☆66Updated 5 years ago
- Code used in 'Exploring the Space of Black-box Attacks on Deep Neural Networks' (https://arxiv.org/abs/1712.09491)☆61Updated 7 years ago