Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering

본문 미리보기

arXiv:2607.25479v1 Announce Type: new Abstract: Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computation graphs are distributed by third parties and reused across downstream services. This reuse model creates a security-critical trust boundary: VLM deployments inherit not only learned parameters but also executable behavior encoded in shared model artifacts. In this pa