YiZeng623 / frequency-backdoorLinks
ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Repo. explores how we can use these artifacts to develop stronger backdoor defenses and attacks.
☆44Updated 3 years ago
Alternatives and similar repositories for frequency-backdoor
Users that are interested in frequency-backdoor are comparing it to the libraries listed below
Sorting:
- Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)☆43Updated 2 years ago
- 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
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆36Updated 9 months ago
- ☆44Updated last year
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆33Updated 2 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆32Updated 2 years ago
- ☆27Updated 2 years ago
- ☆21Updated 2 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 8 months ago
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆30Updated 4 years ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆39Updated last year
- Anti-Backdoor learning (NeurIPS 2021)☆82Updated 2 years ago
- ☆82Updated 4 years ago
- Input-aware Dynamic Backdoor Attack (NeurIPS 2020)☆35Updated last year
- ☆13Updated 3 years ago
- ☆24Updated last year
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 3 years ago
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated 2 years ago
- ☆65Updated last year
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Updated 2 years ago
- An Embarrassingly Simple Backdoor Attack on Self-supervised Learning☆17Updated last year
- Code for "Label-Consistent Backdoor Attacks"☆57Updated 4 years ago
- ☆24Updated 2 years ago
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆127Updated 8 months ago
- CVPR 2021 Official repository for the Data-Free Model Extraction paper. https://arxiv.org/abs/2011.14779☆71Updated last year
- ☆31Updated 3 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
- ☆19Updated 3 years ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 2 years ago