AdelaideAuto-IDLab / Februus
Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems
☆23Updated 3 years ago
Related projects: ⓘ
- This is for releasing the source code of the ACSAC paper "STRIP: A Defence Against Trojan Attacks on Deep Neural Networks"☆47Updated 4 years ago
- 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
- Implementation of Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning paper☆19Updated 4 years ago
- ☆17Updated 2 years ago
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks☆17Updated 5 years ago
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆25Updated 3 years ago
- ☆24Updated last year
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆28Updated 3 months ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆49Updated last year
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)☆47Updated 5 years ago
- Invisible Backdoor Attack with Sample-Specific Triggers☆85Updated 2 years ago
- CVPR 2021 Official repository for the Data-Free Model Extraction paper. https://arxiv.org/abs/2011.14779☆66Updated 5 months ago
- ☆41Updated 2 weeks ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆23Updated 2 years ago
- ☆17Updated 2 years ago
- ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation☆47Updated 2 years ago
- ☆19Updated 2 years ago
- ☆42Updated 11 months ago
- Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".☆28Updated 2 years ago
- ☆19Updated 4 years ago
- Code for "Label-Consistent Backdoor Attacks"☆48Updated 3 years ago
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)☆29Updated 3 years ago
- Official Tensorflow implementation for "Improving Adversarial Transferability via Neuron Attribution-based Attacks" (CVPR 2022)☆33Updated last year
- Official implementation of (CVPR 2022 Oral) Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks.☆26Updated 2 years ago
- Code for "PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier"☆34Updated last year
- ☆73Updated 3 years ago
- ☆48Updated 2 years ago
- A simple implementation of BadNets on MNIST☆31Updated 5 years ago
- ☆15Updated 2 years ago
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆111Updated last month