mlsanityData to 14 Oct 2026

SafeVid: Toward Safety Aligned Video Large Multimodal Models

arXiv 2505.11926 ↗First posted 17 May 2025cs.CV cs.AIcited by 9

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

also in 2 more
Abstract (arXiv)

As Video Large Multimodal Models (VLMMs) rapidly advance, their inherent complexity introduces significant safety challenges, particularly the issue of mismatched generalization where static safety alignments fail to transfer to dynamic video contexts. We introduce SafeVid, a framework designed to instill video-specific safety principles in VLMMs. SafeVid uniquely transfers robust textual safety alignment capabilities to the video domain by employing detailed textual video descriptions as an interpretive bridge, facilitating LLM-based rule-driven safety reasoning. This is achieved through a closed-loop system comprising: 1) generation of SafeVid-350K, a novel 350,000-pair video-specific safety preference dataset; 2) targeted alignment of VLMMs using Direct Preference Optimization (DPO); and 3) comprehensive evaluation via our new SafeVidBench benchmark. Alignment with SafeVid-350K significantly enhances VLMM safety, with models like LLaVA-NeXT-Video demonstrating substantial improvements (e.g., up to 42.39%) on SafeVidBench. SafeVid provides critical resources and a structured approach, demonstrating that leveraging textual descriptions as a conduit for safety reasoning markedly improves the safety alignment of VLMMs. We have made SafeVid-350K dataset (https://huggingface.co/datasets/yxwang/SafeVid-350K) publicly available.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 38 of its 50 references that are in the map. First posted on arXiv 17 May 2025.

Builds on

38 of 50 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks3 Apr
  2. 2023MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models29 Nov

Other references · 36

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2024GPT-4o System Cardcited by 4,588
  7. 2023Qwen Technical Reportcited by 3,344
  8. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  9. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  10. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  11. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  12. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
24 more
  1. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  2. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  3. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  4. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
  5. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 712
  6. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 625
  7. 2021VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understandingcited by 602
  8. 2023InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generationcited by 497
  9. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  10. 2024A StrongREJECT for Empty Jailbreakscited by 385
  11. 2024InternVideo2: Scaling Foundation Models for Multimodal Video Understandingcited by 317
  12. 2024MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understandingcited by 182
  13. 2024Direct Preference Optimization of Video Large Multimodal Models from Language Model Rewardcited by 147
  14. 2024Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?cited by 61
  15. 2024SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Typescited by 60
  16. 2024Large Language Model Safety: A Holistic Surveycited by 59
  17. 2023Fake Alignment: Are LLMs Really Aligned Well?cited by 39
  18. 2023Flames: Benchmarking Value Alignment of LLMs in Chinesecited by 37
  19. 2023GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generationcited by 36
  20. 2024Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedbackcited by 36
  21. 2024SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Modelscited by 23
  22. 2022MovieCLIP: Visual Scene Recognition in Moviescited by 16
  23. 2024Harnessing LLMs for Automated Video Content Analysis: An Exploratory Workflow of Short Videos on Depressioncited by 4
  24. 2025Bypassing Safety Guardrails in LLMs Using Humorcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Modelscited by 21
  2. 2025SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Modelscited by 10
  3. 2026Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignmentcited by 6
  4. 2025Benchmarking the Trustworthiness in Multimodal LLMs for Video Understandingcited by 1
  5. 2026Towards Context-Invariant Safety Alignment for Large Language Modelscited by 0
  6. 2026HarmVideoBench: Benchmarking Harmful Video Understanding in Large Multimodal Modelscited by 0
  7. 2026Child-Oriented AIGC Video Risk Reviewing: A Benchmark and Knowledge-Supported Iterative Reasoning Frameworkcited by 0
  8. 2026Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderationcited by 0
  9. 2026Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
  2. 2025From Evaluation to Defense: Advancing Safety in Video Large Language Models
  3. 2025MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models
  4. 2025SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
  5. 2026ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models
  6. 2024VLSBench: Unveiling Visual Leakage in Multimodal Safety
  7. 2025VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search
  8. 2025Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs