{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/from-evaluation-to-defense-advancing-safety","title":"From Evaluation to Defense: Advancing Safety in Video Large Language Models","arxiv_id":"2505.16643","date":"2025-05-22","proceeding":null,"authors":["Yiwei Sun","Peiqi Jiang","Chuanbin Liu","Luohao Lin","Zhiying Lu","Hongtao Xie"],"abstract":"While the safety risks of image-based large language models have been extensively studied, their video-based counterparts (Video LLMs) remain critically under-examined. To systematically study this problem, we introduce \\textbf{VideoSafetyBench (VSB-77k) - the first large-scale, culturally diverse benchmark for Video LLM safety}, which compromises 77,646 video-query pairs and spans 19 principal risk categories across 10 language communities. \\textit{We reveal that integrating video modality degrades safety performance by an average of 42.3\\%, exposing systemic risks in multimodal attack exploitation.} To address this vulnerability, we propose \\textbf{VideoSafety-R1}, a dual-stage framework achieving unprecedented safety gains through two innovations: (1) Alarm Token-Guided Safety Fine-Tuning (AT-SFT) injects learnable alarm tokens into visual and textual sequences, enabling explicit harm perception across modalities via multitask objectives. (2) Then, Safety-Guided GRPO enhances defensive reasoning through dynamic policy optimization with rule-based rewards derived from dual-modality verification. These components synergize to shift safety alignment from passive harm recognition to active reasoning. The resulting framework achieves a 65.1\\% improvement on VSB-Eval-HH, and improves by 59.1\\%, 44.3\\%, and 15.0\\% on the image safety datasets MMBench, VLGuard, and FigStep, respectively. \\textit{Our codes are available in the supplementary materials.} \\textcolor{red}{Warning: This paper contains examples of harmful language and videos, and reader discretion is recommended.}","url_abs":"https://arxiv.org/abs/2505.16643v1","url_pdf":"https://arxiv.org/pdf/2505.16643v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"safety-alignment","task_name":"Safety Alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.16643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16643"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Emiya-syw/VideoSafety-R1","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"found_in_text":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6bcba94a8d4b15fd","entry":"configure_alarm_tokens","repo":"Emiya-syw/VideoSafety-R1","repo_kind":"found_in_text","path":"videollama3/model/alarm_tokens.py","file_url":"https://github.com/Emiya-syw/VideoSafety-R1/blob/HEAD/videollama3/model/alarm_tokens.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6bcba94a8d4b15fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}