Code for our S&P'21 paper: Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding
☆53Nov 15, 2022Updated 3 years ago
Alternatives and similar repositories for awt
Users that are interested in awt are comparing it to the libraries listed below
Sorting:
- ☆22Mar 19, 2024Updated last year
- Code for the paper "Watermarking Makes Language Models Radioactive"☆21Oct 25, 2024Updated last year
- [USENIX Security'24] REMARK-LLM: A robust and efficient watermarking framework for generative large language models☆27Oct 23, 2024Updated last year
- ☆16Jul 17, 2022Updated 3 years ago
- This is the source code of paper MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compressi…☆115Jun 25, 2024Updated last year
- ☆18Nov 13, 2021Updated 4 years ago
- Code for watermarking language models☆85Sep 7, 2024Updated last year
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆20Sep 9, 2024Updated last year
- Reference implementation of the PRADA model stealing defense. IEEE Euro S&P 2019.☆35Mar 20, 2019Updated 6 years ago
- Provably Secure Steganography in Practice Based on “Distribution Copies”☆42Jun 1, 2025Updated 9 months ago
- This technique modifies image data so that any model trained on it will bear an identifiable mark.☆44Aug 13, 2021Updated 4 years ago
- [ACL2024-Main] Data and Code for WaterBench: Towards Holistic Evaluation of LLM Watermarks☆30Nov 14, 2023Updated 2 years ago
- Evaluating Durability: Benchmark Insights into Multimodal Watermarking☆12Jun 7, 2024Updated last year
- ☆50Feb 27, 2021Updated 5 years ago
- StegaStamp of pytorch version☆71Oct 31, 2023Updated 2 years ago
- Code and data for our paper "Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark"…☆51Jul 11, 2023Updated 2 years ago
- Code for "On the Learnability of Watermarks for Language Models" (ICLR 2024)☆27Feb 15, 2025Updated last year
- Adapting the "Radioactive Data" paper to work for text models☆12Dec 23, 2020Updated 5 years ago
- ☆14Nov 11, 2025Updated 3 months ago
- [EMNLP 2022] Distillation-Resistant Watermarking (DRW) for Model Protection in NLP☆13Aug 17, 2023Updated 2 years ago
- ☆32Jun 6, 2024Updated last year
- Watermarking against model extraction attacks in MLaaS. ACM MM 2021.☆34Jul 15, 2021Updated 4 years ago
- Robustness of DWT vs DCT is graded based on the quality of extracted watermark. The measure used is the Correlation coefficient (0-100%).…☆14Jan 4, 2024Updated 2 years ago
- ☆661Sep 17, 2025Updated 5 months ago
- ☆19Sep 9, 2024Updated last year
- Protect your machine learning models easily and securely with watermarking 🔑☆97Apr 24, 2024Updated last year
- Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models" accepted by ICLR 2024☆34May 23, 2024Updated last year
- Codes for CVPR2020 paper "Towards Transferable Targeted Attack".☆15Apr 24, 2022Updated 3 years ago
- ☆13Jan 30, 2019Updated 7 years ago
- [CCS-LAMPS'24] LLM IP Protection Against Model Merging☆16Oct 14, 2024Updated last year
- ☆16Dec 3, 2021Updated 4 years ago
- Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images, CVPR 2018☆18Jul 3, 2018Updated 7 years ago
- Pytorch implementation of paper "HiDDeN: Hiding Data With Deep Networks" by Jiren Zhu, Russell Kaplan, Justin Johnson, and Li Fei-Fei☆416Aug 8, 2024Updated last year
- Official repository of the paper: Who Wrote this Code? Watermarking for Code Generation (ACL 2024)☆39May 28, 2024Updated last year
- The code of our AAAI 2021 paper "Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-transform Domain"☆16Apr 1, 2021Updated 4 years ago
- [ICLR 2025] Permute-and-Flip: An optimally robust and watermarkable decoder for LLMs☆19Mar 20, 2025Updated 11 months ago
- ☆19Mar 26, 2022Updated 3 years ago
- This is the repositoary for our paper published at ICML24.☆11Jun 11, 2025Updated 8 months ago
- [ICLR 2025] VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking (Official Implementation)☆51May 30, 2025Updated 9 months ago