ssg-research / dawn-dynamic-adversarial-watermarking-of-neural-networks
Watermarking against model extraction attacks in MLaaS. ACM MM 2021.
☆32Updated 3 years ago
Related projects: ⓘ
- Reference implementation of the PRADA model stealing defense. IEEE Euro S&P 2019.☆33Updated 5 years ago
- Website & Documentation: https://sbaresearch.github.io/model-watermarking/☆20Updated 11 months ago
- [CCS'22] SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders☆14Updated 2 years ago
- This is the official implementation of our paper 'Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protecti…☆47Updated 6 months ago
- ☆44Updated 3 years ago
- Defending against Model Stealing via Verifying Embedded External Features☆31Updated 2 years ago
- This is the implementation of our paper 'Open-sourced Dataset Protection via Backdoor Watermarking', accepted by the NeurIPS Workshop on …☆19Updated 2 years ago
- The implement of paper "How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNN…☆23Updated 3 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆30Updated last year
- ☆19Updated 4 years ago
- CVPR 2021 Official repository for the Data-Free Model Extraction paper. https://arxiv.org/abs/2011.14779☆66Updated 5 months ago
- ☆17Updated 2 years ago
- 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
- The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".☆99Updated last year
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)☆29Updated 3 years ago
- PyTorch implementation of our ICLR 2023 paper titled "Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?".☆12Updated last year
- ☆10Updated 3 years ago
- Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems☆23Updated 3 years ago
- ☆15Updated 2 years ago
- Example of the attack described in the paper "Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization"☆22Updated 4 years ago
- The code is for our NeurIPS 2019 paper: https://arxiv.org/abs/1910.04749☆31Updated 4 years ago
- ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation☆47Updated 2 years ago
- ☆19Updated 2 years ago
- Implementation of Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning paper☆19Updated 4 years ago
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks☆17Updated 5 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆49Updated last year
- ☆73Updated 3 years ago
- Implementation of IEEE TNNLS 2023 and Elsevier PR 2023 papers on backdoor watermarking for deep classification models with unambiguity an…☆12Updated last year
- ☆20Updated last year
- 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