Yoruko-Tang / ModelGuard
Official implementation of the USENIX Security 2024 paper ModelGuard: Information-Theoretic Defense Against Model Extraction Attacks.
☆13Updated last year
Alternatives and similar repositories for ModelGuard:
Users that are interested in ModelGuard are comparing it to the libraries listed below
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆25Updated last year
- ☆27Updated 2 years ago
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆124Updated 5 months ago
- [CCS'22] SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders☆19Updated 2 years ago
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)☆30Updated 4 years ago
- Website & Documentation: https://sbaresearch.github.io/model-watermarking/☆23Updated last year
- Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)☆40Updated 2 years ago
- Watermarking against model extraction attacks in MLaaS. ACM MM 2021.☆33Updated 3 years ago
- Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"☆127Updated last year
- ☆24Updated 2 years ago
- ☆12Updated last year
- ☆17Updated 3 years ago
- ☆19Updated 2 years ago
- Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".☆30Updated 3 years ago
- ☆42Updated last year
- Code for "Label-Consistent Backdoor Attacks"☆56Updated 4 years ago
- ☆23Updated 10 months ago
- 复现了下Neural Cleanse这篇论文,真的是简单而有效,发在了okaland☆30Updated 3 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆81Updated last year
- ☆25Updated 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…☆43Updated 3 years ago
- Defending against Model Stealing via Verifying Embedded External Features☆36Updated 3 years ago
- ☆19Updated 3 years ago
- [AAAI 2023] Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network☆28Updated 6 months ago
- ☆27Updated last year
- Code related to the paper "Machine Unlearning of Features and Labels"☆69Updated last year
- ICML 2022 code for "Neurotoxin: Durable Backdoors in Federated Learning" https://arxiv.org/abs/2206.10341☆73Updated 2 years ago
- This is for releasing the source code of the ACSAC paper "STRIP: A Defence Against Trojan Attacks on Deep Neural Networks"☆56Updated 5 months ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 2 years ago
- Invisible Backdoor Attack with Sample-Specific Triggers☆94Updated 2 years ago