TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment

arXiv:2404.11121v1 Announce Type: new
Abstract: Proprietary large language models (LLMs) have been widely applied in various scenarios. Additionally, deploying LLMs on edge devices is trending for efficiency and privacy reasons. However, edge deployment of proprietary LLMs introduces new security challenges: edge-deployed models are exposed as white-box accessible to users, enabling adversaries to conduct effective model stealing (MS) attacks. Unfortunately, existing defense mechanisms fail to provide effective protection. Specifically, we identify four critical protection properties that existing methods fail to simultaneously …

arxiv box challenges cs.ai cs.cr deployment devices edge edge deployment edge devices efficiency exposed language language models large llms privacy safeguarding security security challenges stealing