Related papers: Double-I Watermark: Protecting Model Copyright for…

Deep learning, especially deep neural networks (DNNs), has been widely and successfully adopted in many critical applications for its high effectiveness and efficiency. The rapid development of DNNs has benefited from the existence of some…

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

We study how to watermark LLM outputs, i.e. embedding algorithmically detectable signals into LLM-generated text to track misuse. Unlike the current mainstream methods that work with a fixed LLM, we expand the watermark design space by…

Model watermarking utilizes internal representations to protect the ownership of large language models (LLMs). However, these features inevitably undergo complex distortions during realistic model modifications such as fine-tuning,…

Copyright protection for deep neural networks (DNNs) is an urgent need for AI corporations. To trace illegally distributed model copies, DNN watermarking is an emerging technique for embedding and verifying secret identity messages in the…

To mitigate the potential harms of Large Language Models (LLMs)generated text, researchers have proposed watermarking, a process of embedding detectable signals within text. With watermarking, we can always accurately detect LLM-generated…

Well-performed deep neural networks (DNNs) generally require massive labelled data and computational resources for training. Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN…

Recently, numerous highly-valuable Deep Neural Networks (DNNs) have been trained using deep learning algorithms. To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been…

The prosperity of deep neural networks (DNNs) is largely benefited from open-source datasets, based on which users can evaluate and improve their methods. In this paper, we revisit backdoor-based dataset ownership verification (DOV), which…

We study the problem of watermarking large language models (LLMs) generated text -- one of the most promising approaches for addressing the safety challenges of LLM usage. In this paper, we propose a rigorous theoretical framework to…

The exorbitant cost of training Large language models (LLMs) from scratch makes it essential to fingerprint the models to protect intellectual property via ownership authentication and to ensure downstream users and developers comply with…

Watermarking has recently emerged as an effective strategy for detecting the outputs of large language models (LLMs). Most existing schemes require white-box access to the model's next-token probability distribution, which is typically not…

Federated learning (FL) allows multiple participants to collaboratively build deep learning (DL) models without directly sharing data. Consequently, the issue of copyright protection in FL becomes important since unreliable participants may…

Large Language Models (LLMs) excel in various applications, including text generation and complex tasks. However, the misuse of LLMs raises concerns about the authenticity and ethical implications of the content they produce, such as…

Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing model stealing…

Model merging is a promising lightweight model empowerment technique that does not rely on expensive computing devices (e.g., GPUs) or require the collection of specific training data. Instead, it involves editing different upstream model…

Large language model (LLM) unlearning is critical in real-world applications where it is necessary to efficiently remove the influence of private, copyrighted, or harmful data from some users. Existing utility-centric unlearning metrics…

Backdoor watermarking is a promising paradigm to protect the copyright of deep neural network (DNN) models. In the existing works on this subject, researchers have intensively focused on watermarking robustness, while the concept of…

Recently, Deep Learning (DL) models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property (IP) risks, as models…

Large language models (LLMs) can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset…