# DeHate: A Stable Diffusion-based Multimodal Approach to Mitigate Hate Speech in Images

arXiv: https://arxiv.org/abs/2509.21787 · HTML: https://mlsanity.com/paper/2509.21787/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Predicting the Type and Target of Offensive Posts in Social Media](https://mlsanity.com/paper/1902.09666/) (2019)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [What the DAAM: Interpreting Stable Diffusion Using Cross Attention](https://mlsanity.com/paper/2210.04885/) (2022)
- [DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models](https://mlsanity.com/paper/2303.11681/) (2023)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Exploring Hate Speech Detection in Multimodal Publications](https://mlsanity.com/paper/1910.03814/) (2019)
- [SemEval-2020 Task 8: Memotion Analysis -- The Visuo-Lingual Metaphor!](https://mlsanity.com/paper/2008.03781/) (2020)
- [Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge](https://mlsanity.com/paper/2012.12975/) (2020)
- [Learning Robust Deep Visual Representations from EEG Brain Recordings](https://mlsanity.com/paper/2310.16532/) (2023)
- [UniFusion: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View](https://mlsanity.com/paper/2207.08536/) (2022)
- [FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering](https://mlsanity.com/paper/2305.04329/) (2023)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization](https://mlsanity.com/paper/2206.04007/) (2022)
- [FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering](https://mlsanity.com/paper/2306.05523/) (2023)
- [Memotion 3: Dataset on Sentiment and Emotion Analysis of Codemixed Hindi-English Memes](https://mlsanity.com/paper/2303.09892/) (2023)
- [Single Image LDR to HDR Conversion using Conditional Diffusion](https://mlsanity.com/paper/2307.02814/) (2023)
- [Hater-O-Genius Aggression Classification using Capsule Networks](https://mlsanity.com/paper/2105.11219/) (2021)
- [Towards Best Practice of Interpreting Deep Learning Models for EEG-based Brain Computer Interfaces](https://mlsanity.com/paper/2202.06948/) (2022)
- [Offense Detection in Dravidian Languages using Code-Mixing Index based Focal Loss](https://mlsanity.com/paper/2111.06916/) (2021)
- [Memotion Analysis through the Lens of Joint Embedding](https://mlsanity.com/paper/2111.07074/) (2021)
- [SEPSIS: I Can Catch Your Lies -- A New Paradigm for Deception Detection](https://mlsanity.com/paper/2312.00292/) (2023)
- [MMT: A Multilingual and Multi-Topic Indian Social Media Dataset](https://mlsanity.com/paper/2304.00634/) (2023)

## Built on by (most cited first, 1 of 1)

- [Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping](https://mlsanity.com/paper/2510.09741/) (2025)

## Abstract (arXiv)

The rise in harmful online content not only distorts public discourse but also poses significant challenges to maintaining a healthy digital environment. In response to this, we introduce a multimodal dataset uniquely crafted for identifying hate in digital content. Central to our methodology is the innovative application of watermarked, stability-enhanced, stable diffusion techniques combined with the Digital Attention Analysis Module (DAAM). This combination is instrumental in pinpointing the hateful elements within images, thereby generating detailed hate attention maps, which are used to blur these regions from the image, thereby removing the hateful sections of the image. We release this data set as a part of the dehate shared task. This paper also describes the details of the shared task. Furthermore, we present DeHater, a vision-language model designed for multimodal dehatification tasks. Our approach sets a new standard in AI-driven image hate detection given textual prompts, contributing to the development of more ethical AI applications in social media.