A bibliometric study toward quantitative research assessment of security of machine learning

A Paracha, J Arshad - Information Discovery and Delivery, 2024 - emerald.com
Purpose Advances in machine learning (ML) have made significant contributions to the
development of intelligent and autonomous systems leading to concerns about resilience of …

Understanding Implosion in Text-to-Image Generative Models

W Ding, CY Li, S Shan, BY Zhao, H Zheng - Proceedings of the 2024 on …, 2024 - dl.acm.org
Recent works show that text-to-image generative models are surprisingly vulnerable to a
variety of poisoning attacks. Empirical results find that these models can be corrupted by …

Disguised Copyright Infringement of Latent Diffusion Model

Y Lu, MYR Yang, Z Liu, G Kamath, Y Yu - arXiv preprint arXiv:2404.06737, 2024 - arxiv.org
Copyright infringement may occur when a generative model produces samples substantially
similar to some copyrighted data that it had access to during the training phase. The notion …