# SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation

arXiv: https://arxiv.org/abs/2606.01481 · HTML: https://mlsanity.com/paper/2606.01481/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 48 of its 61 references that are in the map.
- First posted on arXiv 31 May 2026.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 30 of 48)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://mlsanity.com/paper/2311.04145/) (2023)
- [Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?](https://mlsanity.com/paper/2310.10012/) (2023)
- [JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2404.03027/) (2024)
- [MMA-Diffusion: MultiModal Attack on Diffusion Models](https://mlsanity.com/paper/2311.17516/) (2023)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [DreamVideo: Composing Your Dream Videos with Customized Subject and Motion](https://mlsanity.com/paper/2312.04433/) (2023)
- [T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation](https://mlsanity.com/paper/2407.14505/) (2024)
- [Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models](https://mlsanity.com/paper/2305.13873/) (2023)
- [Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models](https://mlsanity.com/paper/2405.04233/) (2024)
- [SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation](https://mlsanity.com/paper/2410.12761/) (2024)
- [ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation](https://mlsanity.com/paper/2402.04324/) (2024)

## Built on by (most cited first, 3 of 3)

- [Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization](https://mlsanity.com/paper/2607.13336/) (2026)
- [Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation](https://mlsanity.com/paper/2608.26535/) (2026)
- [TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks](https://mlsanity.com/paper/2609.31032/) (2026)

## Abstract (arXiv)

With the rapid advancements in text-to-image diffusion models, generative video models (T2V models) like Sora can now produce short synthetic videos from a text prompt or an initial image. However, synthetic video generation -- especially when guided by an initial image -- often poses risks, including the potential creation of illegal, politically sensitive, or unethical content. Existing benchmarks have started to consider the safety of generated videos, but they primarily focus on testing models with malicious text prompts, ignoring the scenario where text prompt and image combination may still lead to harmful video content. In practice, this is a common and challenging issue: videos generated from safe text and image inputs can nonetheless convey harmful information. To bridge this gap, we introduce SafeGen-Bench, a benchmark specifically designed to evaluate the safety of conditional T2V models. Our benchmark defines 10 malicious categories, concentrating on risks related to both temporal sequences and depicted behaviors. SafeGen-Bench consists of carefully selected start frames from diverse image and video sources, paired with corresponding text prompts to simulate realistic inputs. We evaluate a variety of conditional T2V models on SafeGen-Bench, and the results indicate that current models struggle to consistently avoid generating malicious content with unsafety scores reaching up to 44.5, especially under conditions requiring high quality. Furthermore, we assess the effectiveness of both text-based and image-based guardrails on our benchmark, finding that unimodal guardrails alone were insufficient to provide a robust defense, with an 80% failure rate across seven malicious categories. We hope that SafeGen-Bench will foster the development of safer and more controllable conditional T2V models.