reds-lab / Universal_Pert_CertLinks
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 2 years ago
Alternatives and similar repositories for Universal_Pert_Cert
Users that are interested in Universal_Pert_Cert are comparing it to the libraries listed below
Sorting:
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆58Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 2 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated 2 years ago
- ☆19Updated 3 years ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆33Updated 2 years ago
- [NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training☆31Updated 3 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 9 months ago
- ☆11Updated 2 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆82Updated 2 years ago
- ☆19Updated 4 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 …☆19Updated 2 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆32Updated 2 years ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆19Updated 2 years ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 3 years ago
- [ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning☆31Updated last year
- Code for "Label-Consistent Backdoor Attacks"☆58Updated 4 years ago
- ☆27Updated 2 years ago
- Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)☆44Updated 2 years ago
- The implementation of our paper: Composite Adversarial Attacks (AAAI2021)☆30Updated 3 years ago
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Updated 2 years ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆39Updated last year
- Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks☆39Updated 4 years ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 3 years ago
- Adversarial Distributional Training (NeurIPS 2020)☆63Updated 4 years ago
- Code for the paper "Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks"☆12Updated 3 years ago
- ☆60Updated 3 years ago
- ☆19Updated 11 months ago
- ☆21Updated 3 years ago
- Implementation of our ICLR 2021 paper: Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples.☆11Updated 4 years ago