sanjaykariyappa / MAZELinks
Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".
☆31Updated 4 years ago
Alternatives and similar repositories for MAZE
Users that are interested in MAZE are comparing it to the libraries listed below
Sorting:
- CVPR 2021 Official repository for the Data-Free Model Extraction paper. https://arxiv.org/abs/2011.14779☆75Updated last year
- ☆45Updated 2 years ago
- ☆84Updated 4 years ago
- This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks…☆127Updated 3 years ago
- Code for "Label-Consistent Backdoor Attacks"☆57Updated 5 years ago
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆29Updated 4 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆84Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 3 years ago
- Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"☆133Updated 2 years ago
- Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)☆46Updated 2 years ago
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)☆33Updated 5 years ago
- ☆27Updated 3 years ago
- Input-aware Dynamic Backdoor Attack (NeurIPS 2020)☆36Updated last year
- ☆21Updated last year
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆133Updated last year
- Code for the paper: Label-Only Membership Inference Attacks☆67Updated 4 years ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆34Updated 3 years ago
- Defending against Model Stealing via Verifying Embedded External Features☆38Updated 3 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆32Updated 3 years ago
- Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching☆111Updated last year
- 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
- ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation☆51Updated 3 years ago
- ☆34Updated 3 years ago
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆36Updated 2 months ago
- Invisible Backdoor Attack with Sample-Specific Triggers☆104Updated 3 years ago
- ☆28Updated last year
- APBench: A Unified Availability Poisoning Attack and Defenses Benchmark (TMLR 08/2024)☆46Updated 9 months ago
- ☆126Updated 3 months ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆62Updated 2 years ago
- ☆19Updated 3 years ago