AI-secure / Certified-Robustness-SoK-Oldver
This repo keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on popular datasets and paper categorization.
☆99Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for Certified-Robustness-SoK-Oldver
- A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]☆88Updated last year
- Certified defense to adversarial examples using CROWN and IBP. Also includes GPU implementation of CROWN verification algorithm (in PyTor…☆93Updated 3 years ago
- Blackbox attacks for deep neural network models☆70Updated 6 years ago
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks☆166Updated 3 years ago
- Code for "On Adaptive Attacks to Adversarial Example Defenses"☆85Updated 3 years ago
- A unified benchmark problem for data poisoning attacks☆151Updated last year
- Repository for Certified Defenses for Adversarial Patch ICLR-2020☆32Updated 4 years ago
- Attacking a dog vs fish classification that uses transfer learning inceptionV3☆68Updated 6 years ago
- Code for "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks"☆53Updated 4 years ago
- ☆79Updated 3 years ago
- Convex Layerwise Adversarial Training (COLT)☆29Updated 3 years ago
- The code is for our NeurIPS 2019 paper: https://arxiv.org/abs/1910.04749☆31Updated 4 years ago
- Code for paper "Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality".☆122Updated 4 years ago
- [NeurIPS'20 Oral] DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles☆55Updated 2 years ago
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆54Updated 2 years ago
- [NeurIPS 2021] Fast Certified Robust Training with Short Warmup☆23Updated last year
- RayS: A Ray Searching Method for Hard-label Adversarial Attack (KDD2020)☆56Updated 4 years ago
- ☆63Updated 5 years ago
- AAAI 2019 oral presentation☆50Updated 3 months ago
- ☆11Updated 2 years ago
- CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is a robustness metric for deep neural networks☆61Updated 3 years ago
- ATTA (Efficient Adversarial Training with Transferable Adversarial Examples)☆32Updated 4 years ago
- Adversarial Defense for Ensemble Models (ICML 2019)☆61Updated 3 years ago
- ☆62Updated 4 years ago
- [CCS 2021] TSS: Transformation-specific smoothing for robustness certification☆21Updated last year
- Codes for reproducing the black-box adversarial attacks in “ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Network…☆55Updated 5 years ago
- Interval attacks (adversarial ML)☆21Updated 5 years ago
- ☆46Updated 3 years ago
- Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching☆94Updated 3 months ago
- Craft poisoned data using MetaPoison☆47Updated 3 years ago