# AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video Generation

arXiv: https://arxiv.org/abs/2609.06991 · HTML: https://mlsanity.com/paper/2609.06991/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization](https://mlsanity.com/paper/2503.23377/) (2025)
- [Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation](https://mlsanity.com/paper/2510.01284/) (2025)
- [T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models](https://mlsanity.com/paper/2407.05965/) (2024)
- [T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation](https://mlsanity.com/paper/2501.12612/) (2025)
- [SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset](https://mlsanity.com/paper/2406.14477/) (2024)
- [TAVGBench: Benchmarking Text to Audible-Video Generation](https://mlsanity.com/paper/2404.14381/) (2024)
- [VABench: A Comprehensive Benchmark for Audio-Video Generation](https://mlsanity.com/paper/2512.09299/) (2025)
- [JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation](https://mlsanity.com/paper/2602.19163/) (2026)
- [T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation](https://mlsanity.com/paper/2512.21094/) (2025)
- [AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation](https://mlsanity.com/paper/2604.08540/) (2026)
- [T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model](https://mlsanity.com/paper/2510.22300/) (2025)
- [TTA-Bench: A Comprehensive Benchmark for Evaluating Text-to-Audio Models](https://mlsanity.com/paper/2509.02398/) (2025)

## Abstract (arXiv)

Recent text-to-audio-video (T2AV) models jointly generate video, speech, sound effects, and ambience from a single text prompt. This capability poses new challenges for safety evaluation, as unsafe content may be conveyed through the audio track or arise only when the visual and audio tracks are interpreted jointly. Existing safety benchmarks largely focus on either generated video or generated audio in isolation and are therefore not designed to capture these risks. To close this gap, we introduce AV-SafetyBench, the first safety benchmark developed specifically for T2AV generation. AV-SafetyBench comprises a four-axis, 13-category taxonomy and 5,200 manually reviewed prompts that specify visual scenes, speech, and non-speech audio. Our evaluation protocol assesses each output under three views: Full-AV, Video-Only, and Audio-Only. It then uses the Video-Only and Audio-Only judgments to assign Full-AV unsafe outputs to one of four risk sources: Video-Only, Audio-Only, AV-Both, or AV-Joint. We evaluate five open-source T2AV models and validate the automated Full-AV judgments against human annotations. Across the five models, Full-AV Unsafe Rates range from 25.1% to 49.4%. Beyond these aggregate rates, risk-source analysis reveals that, for four of the five models, Audio-Only and AV-Joint cases-unsafe outputs missed by video-only evaluation-account for 41.6-48.3% of Full-AV unsafe outputs for which a risk source could be assigned. In the Cross-Modal Harm Emergence category, AV-Joint accounts for 87.5% of unsafe outputs withan assigned risk source. Together, these findings demonstrate the value of AV-SafetyBench for evaluating T2AV safety across the visual and audio modalities and their interaction.