Authors

* External authors

Venue

Date

Share

CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks

Xuanli He*

Qiongkai Xu*

Yi Zeng

Lingjuan Lyu

Fangzhao Wu*

Jiwei Li*

Ruoxi Jia*

* External authors

NeurIPS 2022

2022

Abstract

Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generation APIs, a recent work has introduced a watermarking algorithm and utilized the null-hypothesis test as a post-hoc ownership verification on the imitation models. However, we find that it is possible to detect those watermarks via sufficient statistics of the frequencies of candidate watermarking words. To address this drawback, in this paper, we propose a novel Conditional wATERmarking framework (CATER) for protecting the IP of text generation APIs. An optimization method is proposed to decide the watermarking rules that can minimize the distortion of overall word distributions while maximizing the change of conditional word selections. Theoretically, we prove that it is infeasible for even the savviest attacker (they know how CATER works) to reveal the used watermarks from a large pool of potential word pairs based on statistical inspection. Empirically, we observe that high-order conditions lead to an exponential growth of suspicious (unused) watermarks, making our crafted watermarks more stealthy. In addition, CATER can effectively identify the IP infringement under architectural mismatch and cross-domain imitation attacks, with negligible impairments on the generation quality of victim APIs. We envision our work as a milestone for stealthily protecting the IP of text generation APIs.

Related Publications

A Simple Background Augmentation Method for Object Detection with Diffusion Model

ECCV, 2024
Yuhang Li, Xin Dong, Chen Chen, Weiming Zhuang, Lingjuan Lyu

In computer vision, it is well-known that a lack of data diversity will impair model performance. In this study, we address the challenges of enhancing the dataset diversity problem in order to benefit various downstream tasks such as object detection and instance segmentati…

Finding a needle in a haystack: A Black-Box Approach to Invisible Watermark Detection

ECCV, 2024
Minzhou Pan*, Zhenting Wang, Xin Dong, Vikash Sehwag, Lingjuan Lyu, Xue Lin*

In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting. WMD is capable of detecting arbitrary watermarks within a given reference dataset using a clean non watermarked dataset as a ref…

PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPR

ICML, 2024
Kartik Patwari, Chen-Nee Chuah*, Lingjuan Lyu, Vivek Sharma

Current image anonymization techniques, largely focus on localized pseudonymization, typically modify identifiable features like faces or full bodies and evaluate anonymity through metrics such as detection and re-identification rates. However, this approach often overlooks …

  • HOME
  • Publications
  • CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.