reds-lab / Universal_Pert_Cert
This repo is the official implementation of the ICLR'23 paper "Towards Robustness Certification Against Universal Perturbations." We calculate the certified robustness against universal perturbations (UAP/ Backdoor) given a trained model.
☆12Updated last year
Related projects ⓘ
Alternatives and complementary repositories for Universal_Pert_Cert
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated last year
- Stable Backdoor Purification (NeurIPS 2023 & 2024)☆23Updated this week
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆55Updated last year
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆14Updated last year
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆18Updated last year
- ☆19Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆50Updated last year
- [ICLR 2021] "Robust Overfitting may be mitigated by properly learned smoothening" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, Shiyu Chan…☆46Updated 2 years ago
- ☆19Updated 2 years ago
- The implementation of our paper: Composite Adversarial Attacks (AAAI2021)☆30Updated 2 years ago
- the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral☆57Updated 3 years ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆28Updated 10 months ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆41Updated 2 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- ☆19Updated 3 years ago
- Code for the CVPR 2020 article "Adversarial Vertex mixup: Toward Better Adversarially Robust Generalization"☆13Updated 4 years ago
- Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".☆28Updated 2 years ago
- Code for the paper "(De)Randomized Smoothing for Certifiable Defense against Patch Attacks" by Alexander Levine and Soheil Feizi.☆17Updated 2 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆31Updated 2 years ago
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆31Updated 3 weeks ago
- Camouflage poisoning via machine unlearning☆15Updated last year
- [ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning☆28Updated 11 months ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆17Updated last year
- ☆17Updated last year
- ☆19Updated last month
- Official Tensorflow implementation for "Improving Adversarial Transferability via Neuron Attribution-based Attacks" (CVPR 2022)☆33Updated last year
- Code for our NeurIPS 2020 paper Backpropagating Linearly Improves Transferability of Adversarial Examples.☆42Updated last year
- ☆53Updated last year
- [NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training☆31Updated 2 years ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆29Updated last year