Related papers: THEMIS: Towards Practical Intellectual Property Pr…

As a valuable digital product, deep neural networks (DNNs) face increasingly severe threats to the intellectual property, making it necessary to develop effective technical measures to protect them. Trigger-based watermarking methods…

DNNs shall be considered as the intellectual property (IP) of the model builder due to the impeding cost of designing/training a highly accurate model. Research attempts have been made to protect the authorship of the trained model and…

Machine learning involves expensive data collection and training procedures. Model owners may be concerned that valuable intellectual property can be leaked if adversaries mount model extraction attacks. As it is difficult to defend against…

Visual Prompt Learning (VPL) differs from traditional fine-tuning methods in reducing significant resource consumption by avoiding updating pre-trained model parameters. Instead, it focuses on learning an input perturbation, a visual…

Graph Neural Networks (GNNs) have become invaluable intellectual property in graph-based machine learning. However, their vulnerability to model stealing attacks when deployed within Machine Learning as a Service (MLaaS) necessitates robust…

Benefiting from the superior capabilities of large language models in natural language understanding and generation, Embeddings-as-a-Service (EaaS) has emerged as a successful commercial paradigm on the web platform. However, prior studies…

As machine- and AI-generated content proliferates, protecting the intellectual property of generative models has become imperative, yet verifying data ownership poses formidable challenges, particularly in cases of unauthorized reuse of…

Mobile devices rely on Trusted Execution Environments (TEEs) to execute security-critical code and protect sensitive assets. This security-critical code is modularized in components known as Trusted Applications (TAs). Vulnerabilities in…

Deep Learning (DL) is finding its way into a growing number of mobile software applications. These software applications, named as DL based mobile applications (abbreviated as mobile DL apps) integrate DL models trained using large-scale…

With the rise in the wholesale adoption of Deep Learning (DL) models in nearly all aspects of society, a unique set of challenges is imposed. Primarily centered around the architectures of these models, these risks pose a significant…

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and Natural Language Processing (NLP) domains. However,…

The rapid advancement of large language models (LLMs) has raised concerns regarding their potential misuse, particularly in generating fake news and misinformation. To address these risks, watermarking techniques for autoregressive language…

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

As Artificial Intelligence as a Service gains popularity, protecting well-trained models as intellectual property is becoming increasingly important. There are two common types of protection methods: ownership verification and usage…

LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit for deployment. In this work we dispute this claim, identifying watermark…

In the rapidly evolving domain of artificial intelligence, safeguarding the intellectual property of Large Language Models (LLMs) is increasingly crucial. Current watermarking techniques against model extraction attacks, which rely on…

With the growth of Internet of Things (IoT) and mo-bile edge computing, billions of smart devices are interconnected to develop applications used in various domains including smart homes, healthcare and smart manufacturing. Deep learning…

Training deep learning models on mobile devices recently becomes possible, because of increasing computation power on mobile hardware and the advantages of enabling high user experiences. Most of the existing work on machine learning at…

Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing…