sokcertifiedrobustness / sokcertifiedrobustness.github.io
Keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on popular datasets
☆17Updated 3 months ago
Related projects: ⓘ
- Code for the paper "(De)Randomized Smoothing for Certifiable Defense against Patch Attacks" by Alexander Levine and Soheil Feizi.☆16Updated 2 years ago
- ☆53Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated last year
- This repo is the official implementation of the ICLR'23 paper "Towards Robustness Certification Against Universal Perturbations." We calc…☆12Updated last year
- Towards Stable Backdoor Purification through Feature Shift Tuning (NeurIPS 2023)☆22Updated last month
- Repository for Certified Defenses for Adversarial Patch ICLR-2020☆32Updated 4 years ago
- ☆11Updated last year
- ☆59Updated 7 months ago
- PyTorch implementation of BPDA+EOT attack to evaluate adversarial defense with an EBM☆23Updated 4 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆49Updated last year
- Code for "PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier"☆34Updated last year
- ATTA (Efficient Adversarial Training with Transferable Adversarial Examples)☆32Updated 4 years ago
- A Leaderboard for Certifiable Robustness against Adversarial Patch Attacks☆19Updated 10 months ago
- A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]☆87Updated last year
- APBench: A Unified Availability Poisoning Attack and Defenses Benchmark (TMLR 08/2024)☆24Updated last month
- Official Tensorflow implementation for "Improving Adversarial Transferability via Neuron Attribution-based Attacks" (CVPR 2022)☆33Updated last year
- ☆20Updated 11 months ago
- [NeurIPS 2021] Fast Certified Robust Training with Short Warmup☆23Updated last year
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆38Updated 2 years ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆16Updated last year
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆14Updated last year
- the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral☆55Updated 3 years ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆25Updated 8 months ago
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆54Updated 2 years ago
- Code for "On Adaptive Attacks to Adversarial Example Defenses"☆84Updated 3 years ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆52Updated last year
- Official Code for Scaling Adversarial Training to Large Perturbation Bounds (ECCV-2022)☆9Updated last year
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆30Updated 2 months ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆18Updated last week
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆23Updated 2 years ago