# Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News

arXiv: https://arxiv.org/abs/2009.07698 · HTML: https://mlsanity.com/paper/2009.07698/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 30 of 42)

- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- [Unbiased Watermark for Large Language Models](https://mlsanity.com/paper/2310.10669/) (2023)
- [NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media](https://mlsanity.com/paper/2104.05893/) (2021)
- [End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models](https://mlsanity.com/paper/2205.12487/) (2022)
- [On the Learnability of Watermarks for Language Models](https://mlsanity.com/paper/2312.04469/) (2023)
- [Detecting Multimedia Generated by Large AI Models: A Survey](https://mlsanity.com/paper/2402.00045/) (2024)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [Multimodal Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2305.13507/) (2023)
- [A Survey on Multimodal Disinformation Detection](https://mlsanity.com/paper/2103.12541/) (2021)
- [Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective](https://mlsanity.com/paper/2210.10488/) (2022)
- [Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?](https://mlsanity.com/paper/2308.01284/) (2023)
- [ConDA: Contrastive Domain Adaptation for AI-generated Text Detection](https://mlsanity.com/paper/2309.03992/) (2023)
- [COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learning](https://mlsanity.com/paper/2101.06278/) (2021)
- [Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?](https://mlsanity.com/paper/2304.01002/) (2023)
- [Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation](https://mlsanity.com/paper/2311.01766/) (2023)
- [Multimodal Misinformation Detection using Large Vision-Language Models](https://mlsanity.com/paper/2407.14321/) (2024)
- [COVID-VTS: Fact Extraction and Verification on Short Video Platforms](https://mlsanity.com/paper/2302.07919/) (2023)
- [DisinfoMeme: A Multimodal Dataset for Detecting Meme Intentionally Spreading Out Disinformation](https://mlsanity.com/paper/2205.12617/) (2022)
- [Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems](https://mlsanity.com/paper/2209.03755/) (2022)
- [Detecting Misinformation in Multimedia Content through Cross-Modal Entity Consistency: A Dual Learning Approach](https://mlsanity.com/paper/2409.00022/) (2024)
- [Machine-Generated Text Localization](https://mlsanity.com/paper/2402.11744/) (2024)
- [Multi-Modal Semantic Inconsistency Detection in Social Media News Posts](https://mlsanity.com/paper/2105.12855/) (2021)
- [Robust Domain Misinformation Detection via Multi-modal Feature Alignment](https://mlsanity.com/paper/2311.14315/) (2023)
- [Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities](https://mlsanity.com/paper/2405.00711/) (2024)
- [Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors](https://mlsanity.com/paper/2503.15128/) (2025)
- [An Overview of Recent Work in Media Forensics: Methods and Threats](https://mlsanity.com/paper/2204.12067/) (2022)
- [Out-of-distribution Evidence-aware Fake News Detection via Dual Adversarial Debiasing](https://mlsanity.com/paper/2304.12888/) (2023)
- [Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures](https://mlsanity.com/paper/2210.01887/) (2022)

## Abstract (arXiv)

Large-scale dissemination of disinformation online intended to mislead or deceive the general population is a major societal problem. Rapid progression in image, video, and natural language generative models has only exacerbated this situation and intensified our need for an effective defense mechanism. While existing approaches have been proposed to defend against neural fake news, they are generally constrained to the very limited setting where articles only have text and metadata such as the title and authors. In this paper, we introduce the more realistic and challenging task of defending against machine-generated news that also includes images and captions. To identify the possible weaknesses that adversaries can exploit, we create a NeuralNews dataset composed of 4 different types of generated articles as well as conduct a series of human user study experiments based on this dataset. In addition to the valuable insights gleaned from our user study experiments, we provide a relatively effective approach based on detecting visual-semantic inconsistencies, which will serve as an effective first line of defense and a useful reference for future work in defending against machine-generated disinformation.