# DISARM: Detecting the Victims Targeted by Harmful Memes

arXiv: https://arxiv.org/abs/2205.05738 · HTML: https://mlsanity.com/paper/2205.05738/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 70 references that are in the map.
- First posted on arXiv 11 May 2022.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Fake News Detection on Social Media: A Data Mining Perspective](https://mlsanity.com/paper/1708.01967/) (2017)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Supervised Multimodal Bitransformers for Classifying Images and Text](https://mlsanity.com/paper/1909.02950/) (2019)
- [Exploring Hate Speech Detection in Multimodal Publications](https://mlsanity.com/paper/1910.03814/) (2019)
- [FANG: Leveraging Social Context for Fake News Detection Using Graph Representation](https://mlsanity.com/paper/2008.07939/) (2020)
- [MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2109.05184/) (2021)
- [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)
- [Detecting and Understanding Harmful Memes: A Survey](https://mlsanity.com/paper/2205.04274/) (2022)
- [A Multimodal Framework for the Detection of Hateful Memes](https://mlsanity.com/paper/2012.12871/) (2020)
- [A Survey on Multimodal Disinformation Detection](https://mlsanity.com/paper/2103.12541/) (2021)
- [Detecting Propaganda Techniques in Memes](https://mlsanity.com/paper/2109.08013/) (2021)
- [Detecting Hate Speech in Multi-modal Memes](https://mlsanity.com/paper/2012.14891/) (2020)
- [Hate Speech Detection: A Solved Problem? The Challenging Case of Long Tail on Twitter](https://mlsanity.com/paper/1803.03662/) (2018)
- [Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions](https://mlsanity.com/paper/1702.01119/) (2017)
- [Detecting Hateful Memes Using a Multimodal Deep Ensemble](https://mlsanity.com/paper/2012.13235/) (2020)
- [Hate Speech in Pixels: Detection of Offensive Memes towards Automatic Moderation](https://mlsanity.com/paper/1910.02334/) (2019)
- [Multimodal Learning for Hateful Memes Detection](https://mlsanity.com/paper/2011.12870/) (2020)

## Built on by (most cited first, 20 of 20)

- [Decoding the Underlying Meaning of Multimodal Hateful Memes](https://mlsanity.com/paper/2305.17678/) (2023)
- [What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memes](https://mlsanity.com/paper/2212.00715/) (2022)
- [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)
- [MEMEX: Detecting Explanatory Evidence for Memes via Knowledge-Enriched Contextualization](https://mlsanity.com/paper/2305.15913/) (2023)
- [SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes](https://mlsanity.com/paper/2412.20541/) (2024)
- [From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment](https://mlsanity.com/paper/2506.18919/) (2025)
- [M-QUEST -- Meme Question-Understanding Evaluation on Semantics and Toxicity](https://mlsanity.com/paper/2603.03315/) (2026)
- [Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: a Case Study on Hateful Memes](https://mlsanity.com/paper/2308.11585/) (2023)
- [On VLMs for Diverse Tasks in Multimodal Meme Classification](https://mlsanity.com/paper/2505.20937/) (2025)
- [SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection](https://mlsanity.com/paper/2509.16060/) (2025)
- [They Said Memes Were Harmless-We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural References](https://mlsanity.com/paper/2602.03822/) (2026)
- [Small Cues, Big Consequences: Learning Pivotal Cues for Multimodal Meme Classification](https://mlsanity.com/paper/2609.26907/) (2026)
- [OSPC: Artificial VLM Features for Hateful Meme Detection](https://mlsanity.com/paper/2407.12836/) (2024)
- [Decoding Memes: Benchmarking Narrative Role Classification across Multilingual and Multimodal Models](https://mlsanity.com/paper/2506.23122/) (2025)
- [Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework](https://mlsanity.com/paper/2602.03268/) (2026)
- [Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges](https://mlsanity.com/paper/2607.19011/) (2026)
- [Token-Region Guided Cross-Attention Fusion for Multimodal Affect Interpretation](https://mlsanity.com/paper/2607.23493/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)

## Abstract (arXiv)

Internet memes have emerged as an increasingly popular means of communication on the Web. Although typically intended to elicit humour, they have been increasingly used to spread hatred, trolling, and cyberbullying, as well as to target specific individuals, communities, or society on political, socio-cultural, and psychological grounds. While previous work has focused on detecting harmful, hateful, and offensive memes, identifying whom they attack remains a challenging and underexplored area. Here we aim to bridge this gap. In particular, we create a dataset where we annotate each meme with its victim(s) such as the name of the targeted person(s), organization(s), and community(ies). We then propose DISARM (Detecting vIctimS targeted by hARmful Memes), a framework that uses named entity recognition and person identification to detect all entities a meme is referring to, and then, incorporates a novel contextualized multimodal deep neural network to classify whether the meme intends to harm these entities. We perform several systematic experiments on three test setups, corresponding to entities that are (a) all seen while training, (b) not seen as a harmful target on training, and (c) not seen at all on training. The evaluation results show that DISARM significantly outperforms ten unimodal and multimodal systems. Finally, we show that DISARM is interpretable and comparatively more generalizable and that it can reduce the relative error rate for harmful target identification by up to 9 points absolute over several strong multimodal rivals.