SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning

by   Peizhuo Lv, et al.

Recent years have witnessed significant success in Self-Supervised Learning (SSL), which facilitates various downstream tasks. However, attackers may steal such SSL models and commercialize them for profit, making it crucial to protect their Intellectual Property (IP). Most existing IP protection solutions are designed for supervised learning models and cannot be used directly since they require that the models' downstream tasks and target labels be known and available during watermark embedding, which is not always possible in the domain of SSL. To address such a problem especially when downstream tasks are diverse and unknown during watermark embedding, we propose a novel black-box watermarking solution, named SSL-WM, for protecting the ownership of SSL models. SSL-WM maps watermarked inputs by the watermarked encoders into an invariant representation space, which causes any downstream classifiers to produce expected behavior, thus allowing the detection of embedded watermarks. We evaluate SSL-WM on numerous tasks, such as Computer Vision (CV) and Natural Language Processing (NLP), using different SSL models, including contrastive-based and generative-based. Experimental results demonstrate that SSL-WM can effectively verify the ownership of stolen SSL models in various downstream tasks. Furthermore, SSL-WM is robust against model fine-tuning and pruning attacks. Lastly, SSL-WM can also evade detection from evaluated watermark detection approaches, demonstrating its promising application in protecting the IP of SSL models.


page 10

page 12

page 17


AWEncoder: Adversarial Watermarking Pre-trained Encoders in Contrastive Learning

As a self-supervised learning paradigm, contrastive learning has been wi...

Evaluating Representations with Readout Model Switching

Although much of the success of Deep Learning builds on learning good re...

On the Difficulty of Defending Self-Supervised Learning against Model Extraction

Self-Supervised Learning (SSL) is an increasingly popular ML paradigm th...

Knowledge-integrated AutoEncoder Model

Data encoding is a common and central operation in most data analysis ta...

Stain-Adaptive Self-Supervised Learning for Histopathology Image Analysis

It is commonly recognized that color variations caused by differences in...

Prompt-Tuning Decision Transformer with Preference Ranking

Prompt-tuning has emerged as a promising method for adapting pre-trained...

Learning Representations on Logs for AIOps

AI for IT Operations (AIOps) is a powerful platform that Site Reliabilit...

Please sign up or login with your details

Forgot password? Click here to reset