dnn-security / Watermark-Robustness-ToolboxLinks
The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".
☆115Updated 2 years ago
Alternatives and similar repositories for Watermark-Robustness-Toolbox
Users that are interested in Watermark-Robustness-Toolbox are comparing it to the libraries listed below
Sorting:
- Invisible Backdoor Attack with Sample-Specific Triggers☆94Updated 2 years ago
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆124Updated 6 months ago
- Website & Documentation: https://sbaresearch.github.io/model-watermarking/☆23Updated last year
- This is the official implementation of our paper 'Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protecti…☆55Updated last year
- The implement of paper "How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNN…☆24Updated 4 years ago
- ☆44Updated last year
- ☆47Updated 4 years ago
- ☆87Updated 4 years ago
- ☆38Updated 3 years ago
- Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems☆28Updated 4 years ago
- [NDSS 2025] Official code for our paper "Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Wate…☆37Updated 7 months ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 2 years ago
- Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"☆127Updated last year
- Defending against Model Stealing via Verifying Embedded External Features☆36Updated 3 years ago
- ☆31Updated 4 years ago
- Code for the paper: Label-Only Membership Inference Attacks☆65Updated 3 years ago
- [AAAI 2023] Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network☆29Updated 7 months ago
- [AAAI 2024] Data-Free Hard-Label Robustness Stealing Attack☆13Updated last year
- This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks…☆122Updated 3 years ago
- This code is the official implementation of WEvade.☆39Updated last year
- Implementation of IEEE TNNLS 2023 and Elsevier PR 2023 papers on backdoor watermarking for deep classification models with unambiguity an…☆17Updated last year
- This is for releasing the source code of the ACSAC paper "STRIP: A Defence Against Trojan Attacks on Deep Neural Networks"☆57Updated 6 months ago
- Webank AI☆41Updated 3 months ago
- Watermarking against model extraction attacks in MLaaS. ACM MM 2021.☆33Updated 3 years ago
- Code for ML Doctor☆88Updated 9 months ago
- CVPR 2021 Official repository for the Data-Free Model Extraction paper. https://arxiv.org/abs/2011.14779☆72Updated last year
- Anti-Backdoor learning (NeurIPS 2021)☆81Updated last year
- Code for "Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment" (CCS 2019)☆47Updated 5 years ago
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)☆31Updated 4 years ago
- This repository contains Python code for the paper "Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearni…☆15Updated last year