Adaptive and Robust Watermark for Generative Tabular Data
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912707385491456 |
|---|---|
| author | Ngo, Dung Daniel Ray, Archan Seshadri, Akshay Scott, Daniel Obitayo, Saheed Kumar, Niraj Potluru, Vamsi K. Pistoia, Marco Veloso, Manuela |
| author_facet | Ngo, Dung Daniel Ray, Archan Seshadri, Akshay Scott, Daniel Obitayo, Saheed Kumar, Niraj Potluru, Vamsi K. Pistoia, Marco Veloso, Manuela |
| contents | In recent years, watermarking generative tabular data has become a prominent framework to protect against the misuse of synthetic data. However, while most prior work in watermarking methods for tabular data demonstrate a wide variety of desirable properties (e.g., high fidelity, detectability, robustness), the findings often emphasize empirical guarantees against common oblivious and adversarial attacks. In this paper, we study a flexible and robust watermarking algorithm for generative tabular data. Specifically, we demonstrate theoretical guarantees on the performance of the algorithm on metrics like fidelity, detectability, robustness, and hardness of decoding. The proof techniques introduced in this work may be of independent interest and may find applicability in other areas of machine learning. Finally, we validate our theoretical findings on synthetic and real-world tabular datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14700 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive and Robust Watermark for Generative Tabular Data Ngo, Dung Daniel Ray, Archan Seshadri, Akshay Scott, Daniel Obitayo, Saheed Kumar, Niraj Potluru, Vamsi K. Pistoia, Marco Veloso, Manuela Cryptography and Security In recent years, watermarking generative tabular data has become a prominent framework to protect against the misuse of synthetic data. However, while most prior work in watermarking methods for tabular data demonstrate a wide variety of desirable properties (e.g., high fidelity, detectability, robustness), the findings often emphasize empirical guarantees against common oblivious and adversarial attacks. In this paper, we study a flexible and robust watermarking algorithm for generative tabular data. Specifically, we demonstrate theoretical guarantees on the performance of the algorithm on metrics like fidelity, detectability, robustness, and hardness of decoding. The proof techniques introduced in this work may be of independent interest and may find applicability in other areas of machine learning. Finally, we validate our theoretical findings on synthetic and real-world tabular datasets. |
| title | Adaptive and Robust Watermark for Generative Tabular Data |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2409.14700 |