后门藏身何处？语音语言模型中后门传播的组件级分析
Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
AI总结：
本文通过后门攻击视角，对语音语言模型进行组件级分析，揭示后门在不同组件中的传播机制，发现后门持久性高度依赖目标组件，且中毒样本与良性样本在共享嵌入中不可直接分离。
摘要：
语音语言模型（SLM）是系统的系统：独立组件联合起来实现共同目标。尽管其异构性，SLM 通常被端到端研究；信息如何流经管道仍然模糊。我们通过后门攻击的视角研究这一问题。我们首先确定后门可以通过 SLM 传播，使所有任务高度脆弱。由此，我们设计了一个组件分析来发现每个组件在后门学习中的作用。我们发现后门的持久性或擦除高度依赖于目标组件。除了传播，我们研究了后门如何在共享的多任务嵌入中被编码，表明中毒样本与良性样本不可直接分离，挑战了过滤防御中常用的可分离性假设。我们的发现强调需要将多模态管道视为具有独特脆弱性的复杂系统，而不仅仅是单模态系统的扩展。
英文摘要：
Speech language models (SLMs) are systems of systems: independent components that unite to achieve a common goal. Despite their heterogeneous nature, SLMs are often studied end-to-end; how information flows through the pipeline remains obscure. We investigate this question through the lens of backdoor attacks. We first establish that backdoors can propagate through the SLM, leaving all tasks highly vulnerable. From this, we design a component analysis to discover the role each component takes in backdoor learning. We find that backdoor persistence or erasure is highly dependent on the targeted component. Beyond propagation, we examine how backdoors are encoded in shared multitask embeddings, showing that poisoned samples are not directly separable from benign ones, challenging a common separability assumption used in filtering defenses. Our findings emphasize the need to treat multimodal pipelines as intricate systems with unique vulnerabilities, not solely extensions of unimodal ones.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
