arXiv (All)
open access
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
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model#187257
- Federated Binary Gating with Server-Side Vision-Language Inference for Surveillance Anomaly Classification#984329
- PlaylistEval: Can Video-Language Judges Be Trusted at Day Scale and Beyond?#1119387
- GaitSpoofNet: advanced spatio-temporal architectures for vision-based presentation attack detection.#371421
- Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis#1105400
Record · ID 985694
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive