AI RESEARCH
Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
arXiv CS.CL
•
ArXi:2510.01157v3 Announce Type: replace 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 reveal the role each component takes in backdoor learning.