Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation 事件

Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation arXiv:2605.30365v1 Announce Type: cross Abstract: Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption dataset. This design introduces an integrity dependency on the music knowledge database. We show that an attacker can poison the database by injecting a small number of crafted music captions, causing the system to retrieve malici