Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Models 文章

ArXiv CS.AI2026-08-12PAPERen作者: Shuozhe Cheng, Kunlan Xiang, Mingxuan Li, Ji Zhang, Dongxiao Liu, Wenbo Jiang

大语言模型

查看原文 →

Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Models · 相关技术

相关技术

Large language model semantic inducement text-based DoS attacks perturbation-based DoS attack TTS ASR speech model security adversarial suffix Prompt 工程 LLM denial-of-service (DoS) attack