SOURCE-LINKED INTELLIGENCE

Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Visual Question Answering (VQA) with Vision-Language Models (VLMs) is increasingly used in privacy-sensitive and bandwidth-constrained settings. Federated Learning (FL), Split Learning (SL), and U-Shaped Split Learning (USL) keep raw data local, but transmitting all visual tokens across a model partition remains costly and can expose private information. We propose QPriv-VL, a question-guided, privacy-aware token-pruning framework for FL, SL, and USL that prunes visual tokens before transmission based on task utility and privacy sensitivity. Its core component is a lightweight Dynamic Threshol

Read original source ↗ Open in workspace

recordType

paper

region

Global