AI RESEARCH
BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation
arXiv CS.LG
•
ArXi:2510.20792v4 Announce Type: replace The rapid progress of graph generation has raised new security concerns, particularly regarding backdoor vulnerabilities. While prior work has explored backdoor attacks in image diffusion and unconditional graph generation, conditional, especially text-guided graph generation remains largely unexamined. This paper proposes BadGraph, a backdoor attack method against latent diffusion models for text-guided graph generation. BadGraph leverages textual triggers to poison.