# Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combine

arXiv: https://arxiv.org/abs/2607.00576 · HTML: https://mlsanity.com/paper/2607.00576/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 39 references that are in the map.
- First posted on arXiv 1 Jul 2026.

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

- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding](https://mlsanity.com/paper/2406.09411/) (2024)
- [MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models](https://mlsanity.com/paper/2408.02718/) (2024)
- [VLSBench: Unveiling Visual Leakage in Multimodal Safety](https://mlsanity.com/paper/2411.19939/) (2024)
- [LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models](https://mlsanity.com/paper/2406.05113/) (2024)
- [Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback](https://mlsanity.com/paper/2503.17682/) (2025)
- [MiCo: Multi-image Contrast for Reinforcement Visual Reasoning](https://mlsanity.com/paper/2506.22434/) (2025)
- [MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning](https://mlsanity.com/paper/2603.02024/) (2026)
- [A Collaborative Content Moderation Framework for Toxicity Detection based on Conformalized Estimates of Annotation Disagreement](https://mlsanity.com/paper/2411.04090/) (2024)
- [Scaling Reinforcement Learning for Content Moderation with Large Language Models](https://mlsanity.com/paper/2512.20061/) (2025)
- [The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning](https://mlsanity.com/paper/2601.14127/) (2026)
- [Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling](https://mlsanity.com/paper/2510.15068/) (2025)

## Abstract (arXiv)

Multi-image content has become an increasingly prevalent form of visual communication in social media, giving rise to a new safety issue, multi-image implicit toxicity (MIIT), where each image appears benign in isolation, but harmful semantics emerge when the images are interpreted jointly. MIIT is particularly challenging for existing commercial moderation APIs and models due to the lack of explicit risky cues in each image. This paper aims to study how to identify MIIT. We first provide a formal definition of MIIT and analyze three key challenges for its detection. To alleviate the scarcity of data in this area, we construct MIIT-dataset, an image-only multi-image safety dataset covering seven representative risk categories through an automatic generation pipeline. Finally, we train MiShield with progressively distilled reasoning supervision, enabling it to produce safety judgments accompanied by explicit analyses of the correlated entities that result in the hazards. Experiments show that MiShield-8B models outperform representative moderation services and even larger-scale models, revealing its effectiveness and practical value for this widely used visual format. Warning: This paper contains potentially sensitive content.