# Detecting and Understanding Harmful Memes: A Survey

arXiv: https://arxiv.org/abs/2205.04274 · HTML: https://mlsanity.com/paper/2205.04274/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 126 references that are in the map.
- First posted on arXiv 9 May 2022.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [Predicting the Type and Target of Offensive Posts in Social Media](https://mlsanity.com/paper/1902.09666/) (2019)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Automated Fact-Checking for Assisting Human Fact-Checkers](https://mlsanity.com/paper/2103.07769/) (2021)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Fine-Grained Analysis of Propaganda in News Articles](https://mlsanity.com/paper/1910.02517/) (2019)
- [Exploring Hate Speech Detection in Multimodal Publications](https://mlsanity.com/paper/1910.03814/) (2019)
- [Automated Fact Checking: Task formulations, methods and future directions](https://mlsanity.com/paper/1806.07687/) (2018)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2109.05184/) (2021)
- [Explainable Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2011.03870/) (2020)
- [Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2110.00413/) (2021)
- [A Survey on Stance Detection for Mis- and Disinformation Identification](https://mlsanity.com/paper/2103.00242/) (2021)
- [A Survey on Computational Propaganda Detection](https://mlsanity.com/paper/2007.08024/) (2020)
- [Characterizing and Detecting Hateful Users on Twitter](https://mlsanity.com/paper/1803.08977/) (2018)
- [SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images](https://mlsanity.com/paper/2105.09284/) (2021)
- [A Survey on Multimodal Disinformation Detection](https://mlsanity.com/paper/2103.12541/) (2021)
- [Disentangling Hate in Online Memes](https://mlsanity.com/paper/2108.06207/) (2021)
- [Detecting Propaganda Techniques in Memes](https://mlsanity.com/paper/2109.08013/) (2021)
- [Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution](https://mlsanity.com/paper/2012.08290/) (2020)
- [Hate Speech in Pixels: Detection of Offensive Memes towards Automatic Moderation](https://mlsanity.com/paper/1910.02334/) (2019)

## Built on by (most cited first, 30 of 58)

- [Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features](https://mlsanity.com/paper/2210.05916/) (2022)
- [GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse](https://mlsanity.com/paper/2401.01523/) (2024)
- [Decoding the Underlying Meaning of Multimodal Hateful Memes](https://mlsanity.com/paper/2305.17678/) (2023)
- [Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking](https://mlsanity.com/paper/2301.11843/) (2023)
- [On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning](https://mlsanity.com/paper/2212.06573/) (2022)
- [MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili](https://mlsanity.com/paper/2408.03468/) (2024)
- [Towards Low-Resource Harmful Meme Detection with LMM Agents](https://mlsanity.com/paper/2411.05383/) (2024)
- [Can GPT-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles](https://mlsanity.com/paper/2402.17478/) (2024)
- [DISARM: Detecting the Victims Targeted by Harmful Memes](https://mlsanity.com/paper/2205.05738/) (2022)
- [ArAIEval Shared Task: Persuasion Techniques and Disinformation Detection in Arabic Text](https://mlsanity.com/paper/2311.03179/) (2023)
- [Large Language Models for Propaganda Span Annotation](https://mlsanity.com/paper/2311.09812/) (2023)
- [Overview of the WANLP 2022 Shared Task on Propaganda Detection in Arabic](https://mlsanity.com/paper/2211.10057/) (2022)
- [What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memes](https://mlsanity.com/paper/2212.00715/) (2022)
- [Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models](https://mlsanity.com/paper/2401.13298/) (2024)
- [LAraBench: Benchmarking Arabic AI with Large Language Models](https://mlsanity.com/paper/2305.14982/) (2023)
- [VerifAI: Verified Generative AI](https://mlsanity.com/paper/2307.02796/) (2023)
- [MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection](https://mlsanity.com/paper/2507.06908/) (2025)
- [Characterizing the Entities in Harmful Memes: Who is the Hero, the Villain, the Victim?](https://mlsanity.com/paper/2301.11219/) (2023)
- [Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities](https://mlsanity.com/paper/2406.07353/) (2024)
- [Towards Comprehensive Detection of Chinese Harmful Memes](https://mlsanity.com/paper/2410.02378/) (2024)
- [MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing](https://mlsanity.com/paper/2405.11215/) (2024)
- [Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study](https://mlsanity.com/paper/2505.15389/) (2025)
- [ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in Videos](https://mlsanity.com/paper/2508.06570/) (2025)
- [ArAIEval Shared Task: Propagandistic Techniques Detection in Unimodal and Multimodal Arabic Content](https://mlsanity.com/paper/2407.04247/) (2024)
- [MemeIntel: Explainable Detection of Propagandistic and Hateful Memes](https://mlsanity.com/paper/2502.16612/) (2025)
- [MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation](https://mlsanity.com/paper/2403.14652/) (2024)
- [Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMs](https://mlsanity.com/paper/2409.07246/) (2024)
- [MemeFier: Dual-stage Modality Fusion for Image Meme Classification](https://mlsanity.com/paper/2304.02906/) (2023)
- [Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification](https://mlsanity.com/paper/2501.15321/) (2025)
- [MemeLens: Multilingual Multitask VLMs for Memes](https://mlsanity.com/paper/2601.12539/) (2026)

## Abstract (arXiv)

The automatic identification of harmful content online is of major concern for social media platforms, policymakers, and society. Researchers have studied textual, visual, and audio content, but typically in isolation. Yet, harmful content often combines multiple modalities, as in the case of memes, which are of particular interest due to their viral nature. With this in mind, here we offer a comprehensive survey with a focus on harmful memes. Based on a systematic analysis of recent literature, we first propose a new typology of harmful memes, and then we highlight and summarize the relevant state of the art. One interesting finding is that many types of harmful memes are not really studied, e.g., such featuring self-harm and extremism, partly due to the lack of suitable datasets. We further find that existing datasets mostly capture multi-class scenarios, which are not inclusive of the affective spectrum that memes can represent. Another observation is that memes can propagate globally through repackaging in different languages and that they can also be multilingual, blending different cultures. We conclude by highlighting several challenges related to multimodal semiotics, technological constraints, and non-trivial social engagement, and we present several open-ended aspects such as delineating online harm and empirically examining related frameworks and assistive interventions, which we believe will motivate and drive future research.