SoftWiser-group / FTrojanLinks
Implementation of An Invisible Black-box Backdoor Attack through Frequency Domain
☆20Updated 3 years ago
Alternatives and similar repositories for FTrojan
Users that are interested in FTrojan are comparing it to the libraries listed below
Sorting:
- The official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabili…☆20Updated last year
- ☆18Updated 4 years ago
- ☆23Updated 5 years ago
- Code for Prior-Guided Adversarial Initialization for Fast Adversarial Training (ECCV2022)☆28Updated 3 years ago
- Code for Transferable Unlearnable Examples☆23Updated 2 years ago
- ☆19Updated 3 years ago
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks☆18Updated 6 years ago
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆29Updated 4 years ago
- Defending against Model Stealing via Verifying Embedded External Features☆38Updated 3 years ago
- Source of the ECCV22 paper "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity"☆18Updated 9 months ago
- [CVPR 2023] The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robust…☆24Updated 2 years ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆46Updated 3 years ago
- PyTorch implementation of our ICLR 2023 paper titled "Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?".☆12Updated 2 years ago
- ☆15Updated 2 years ago
- code for "Feature Importance-aware Transferable Adversarial Attacks"☆87Updated 3 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 3 years ago
- Invisible Backdoor Attack with Sample-Specific Triggers☆103Updated 3 years ago
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆36Updated 2 months ago
- ☆45Updated 2 years ago
- Spectrum simulation attack (ECCV'2022 Oral) towards boosting the transferability of adversarial examples☆114Updated 3 years ago
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Updated 3 years ago
- ☆16Updated 4 years ago
- Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)☆118Updated 3 years ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆34Updated 3 years ago
- A curated list of papers for the transferability of adversarial examples☆75Updated last year
- Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.☆61Updated 3 years ago
- A Unified Approach to Interpreting and Boosting Adversarial Transferability (ICLR2021)☆31Updated 3 years ago
- ☆37Updated last year
- This is the official implementation of our paper 'Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protecti…☆58Updated last year
- Simple yet effective targeted transferable attack (NeurIPS 2021)☆51Updated 3 years ago