Pointncbw: Towards dataset ownership verification for point clouds via negative clean-label backdoor watermark

C Wei, Y Wang, K Gao, S Shao, Y Li… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recently, point clouds have been widely used in computer vision, whereas their collection is
time-consuming and expensive. As such, point cloud datasets are the valuable intellectual …

Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks

Y He, B Li, Y Wang, M Yang, J Wang, H Hu… - Proceedings of the 2024 …, 2024 - dl.acm.org
The vulnerability of machine learning models to Membership Inference Attacks (MIAs) has
garnered considerable attention in recent years. These attacks determine whether a data …

Watermarking Large Language Models and the Generated Content: Opportunities and Challenges

R Zhang, F Koushanfar - arXiv preprint arXiv:2410.19096, 2024 - arxiv.org
The widely adopted and powerful generative large language models (LLMs) have raised
concerns about intellectual property rights violations and the spread of machine-generated …

DEEPREG: A Trustworthy and Privacy-Friendly Ownership Regulatory Framework for Deep Learning Models

X Zhuang, L Zhang, C Tang, Y Li - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Well-trained deep learning (DL) models are widely recognized as valuable intellectual
property (IP) and have been extensively adopted. However, concerns regarding IP …

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

Z Wang, V Sehwag, C Chen, L Lyu… - arXiv preprint arXiv …, 2024 - arxiv.org
Latent generative models (eg, Stable Diffusion) have become more and more popular, but
concerns have arisen regarding potential misuse related to images generated by these …

Unharmful Backdoor-based Client-side Watermarking in Federated Learning

K Luo, KH Chow - arXiv preprint arXiv:2410.21179, 2024 - arxiv.org
Protecting intellectual property (IP) in federated learning (FL) is increasingly important as
clients contribute proprietary data to collaboratively train models. Model watermarking …

SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI

K Ren, Z Yang, L Lu, J Liu, Y Li, J Wan, X Zhao… - arXiv preprint arXiv …, 2024 - arxiv.org
The rapid advancement of AI technology, particularly in generating AI-generated content
(AIGC), has transformed numerous fields, eg, art video generation, but also brings new risks …

NSmark: Null Space Based Black-box Watermarking Defense Framework for Pre-trained Language Models

H Zhao, J Hu, P Li, F Li, J Sha, P Chen, Z Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Pre-trained language models (PLMs) have emerged as critical intellectual property (IP)
assets that necessitate protection. Although various watermarking strategies have been …