# AIRD: Adversarial Learning Framework for Image Repurposing Detection

arXiv: https://arxiv.org/abs/1903.00788 · HTML: https://mlsanity.com/paper/1903.00788/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2019.

## Built on by (most cited first, 7 of 7)

- [SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2403.03170/) (2024)
- [Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation](https://mlsanity.com/paper/2311.01766/) (2023)
- [Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection](https://mlsanity.com/paper/2412.14686/) (2024)
- [BioFors: A Large Biomedical Image Forensics Dataset](https://mlsanity.com/paper/2108.12961/) (2021)
- [Verifying Cross-modal Entity Consistency in News using Vision-language Models](https://mlsanity.com/paper/2501.11403/) (2025)
- [Image-Text Out-Of-Context Detection Using Synthetic Multimodal Misinformation](https://mlsanity.com/paper/2403.08783/) (2024)
- [A Review of Web Infodemic Analysis and Detection Trends across Multi-modalities using Deep Neural Networks](https://mlsanity.com/paper/2112.00803/) (2021)

## Abstract (arXiv)

Image repurposing is a commonly used method for spreading misinformation on social media and online forums, which involves publishing untampered images with modified metadata to create rumors and further propaganda. While manual verification is possible, given vast amounts of verified knowledge available on the internet, the increasing prevalence and ease of this form of semantic manipulation call for the development of robust automatic ways of assessing the semantic integrity of multimedia data. In this paper, we present a novel method for image repurposing detection that is based on the real-world adversarial interplay between a bad actor who repurposes images with counterfeit metadata and a watchdog who verifies the semantic consistency between images and their accompanying metadata, where both players have access to a reference dataset of verified content, which they can use to achieve their goals. The proposed method exhibits state-of-the-art performance on location-identity, subject-identity and painting-artist verification, showing its efficacy across a diverse set of scenarios.