cs.CVNov 11, 2026

Beyond the Explicit: Benchmarking and Detecting Implicit Harm in Short Videos

Authors: Chenyang Li, Qifan Yu, Saihui Hou, Zhaofeng He

Organizations: Beijing University of Posts and Telecommunications, Beijing, China · Beijing Normal University, Beijing, China

Abstract

Short videos have become a dominant online medium, where harmful content is increasingly conveyed in implicit and fragmented forms. Prior work largely focuses on explicit categories, such as violence and hate speech, and often fails to detect videos that subtly promote misleading values through narrative context, emotional framing, or cross-modal cues, partly due to the lack of dedicated benchmarks for implicit harm. To bridge this gap, we construct DeepHarm-7K, a large-scale harmful short-video dataset comprising 7,110 samples annotated according to a fine-grained harmful-content taxonomy. The dataset systematically covers implicitly harmful videos across diverse real-world scenarios and is constructed through a rigorous multi-stage quality-control process. Building on this dataset, we propose DeepHarm-VL, a multimodal detection framework that integrates visual, audio, and cross-modal reasoning. The framework employs a two-round reasoning strategy to progressively identify surface-level evidence and infer latent harmful implications. Experimental results show consistent improvements over strong baselines and state-of-the-art methods across multiple open-source video-language models, demonstrating its effectiveness in detecting both explicit and implicit harmful short videos.

Figures & tables

Explore similar work

CardsList
  1. HarmVideoBench: Benchmarking Harmful Video Understanding in Large Multimodal Models

    Jun 25, 2026Jiajun Wu, Haoyu Kang, Yining Sun +13Video UnderstandingVideo Content Moderation

  2. Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators

    Nov 6, 2024Claire Wonjeong Jo, Miki Wesołowska, Magdalena WojcieszakVideo Content ModerationLLM-Assisted Annotation

  3. Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation

    Aug 31, 2026Ruotong Wang, Zihao Zhu, Siwei Lyu +2Multimodal Large Language ModelsVideo Content Moderation