SOURCE-LINKED INTELLIGENCE
Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?
Video Large Language Models (VideoLLMs) are increasingly deployed in safety-critical applications such as content moderation and video analytics. To process long videos efficiently, VideoLLMs rely on frame sampling, token compression, and modality fusion, which together form an observation pipeline that reduces the raw video to a compact internal representation. Recent observation-level attacks exploit this pipeline to prevent the model from perceiving harmful content, yet no defense has been explicitly designed for this threat. We introduce DefTEval, a controlled evaluation framework that sys
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-08T06:59:19.000Z
First collected: 2026-09-20T20:22:01.598Z. This is not the publication date.