AI-secure / VeriGaugeLinks
A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]
☆90Updated 2 years ago
Alternatives and similar repositories for VeriGauge
Users that are interested in VeriGauge are comparing it to the libraries listed below
Sorting:
- This repo keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on …☆98Updated 2 years ago
- Certified defense to adversarial examples using CROWN and IBP. Also includes GPU implementation of CROWN verification algorithm (in PyTor…☆98Updated 4 years ago
- Code for "On Adaptive Attacks to Adversarial Example Defenses"☆86Updated 4 years ago
- Library for training globally-robust neural networks.☆28Updated 3 weeks ago
- [CCS 2021] TSS: Transformation-specific smoothing for robustness certification☆26Updated last year
- A unified benchmark problem for data poisoning attacks☆157Updated last year
- [NeurIPS 2021] Fast Certified Robust Training with Short Warmup☆25Updated 2 months ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆58Updated 2 years ago
- The code is for our NeurIPS 2019 paper: https://arxiv.org/abs/1910.04749☆34Updated 5 years ago
- Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching☆108Updated last year
- ☆66Updated 4 years ago
- ☆66Updated 6 years ago
- ☆11Updated 2 years ago
- Attacking a dog vs fish classification that uses transfer learning inceptionV3☆70Updated 7 years ago
- Code release for DeepJudge (S&P'22)☆51Updated 2 years ago
- ☆10Updated 4 years ago
- Repository for Certified Defenses for Adversarial Patch ICLR-2020☆33Updated 4 years ago
- This repo is the official implementation of the ICLR'23 paper "Towards Robustness Certification Against Universal Perturbations." We calc…☆12Updated 2 years ago
- Craft poisoned data using MetaPoison☆53Updated 4 years ago
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆55Updated 3 years ago
- Official TensorFlow implementation of "Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization" (ICML 2019)☆40Updated 4 years ago
- This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks…☆122Updated 3 years ago
- Code for the paper "(De)Randomized Smoothing for Certifiable Defense against Patch Attacks" by Alexander Levine and Soheil Feizi.☆17Updated 3 years ago
- MACER: MAximizing CErtified Radius (ICLR 2020)☆30Updated 5 years ago
- ☆98Updated 4 years ago
- ☆66Updated last year
- Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks☆39Updated 4 years ago
- ☆23Updated last year
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- ☆82Updated 4 years ago