音声モデルの脆弱性

When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

Authors: Bodam Kim, Hiskias Dingeto, Taeyoun Kwon, Dasol Choi, DongGeon Lee, Haon Park, JaeHoon Lee, Jongho Shin | Published: 2025-08-05

Prompt Injection

Attack Evaluation

音声モデルの脆弱性

2025.08.05 2025.08.07

Literature Database