# Generative AI Literacy Training Improves Intelligence Analysts' Discrimination of Real and AI-Generated Images

arXiv: https://arxiv.org/abs/2606.28510 · HTML: https://mlsanity.com/paper/2606.28510/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 46 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 16 of 16)

- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Raising the Bar of AI-generated Image Detection with CLIP](https://mlsanity.com/paper/2312.00195/) (2023)
- [Intriguing properties of synthetic images: from generative adversarial networks to diffusion models](https://mlsanity.com/paper/2304.06408/) (2023)
- [Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowds](https://mlsanity.com/paper/2105.06496/) (2021)
- [Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024](https://mlsanity.com/paper/2503.02857/) (2025)
- [More Real than Real: A Study on Human Visual Perception of Synthetic Faces](https://mlsanity.com/paper/2106.07226/) (2021)
- [AI-Generated Image Detection using a Cross-Attention Enhanced Dual-Stream Network](https://mlsanity.com/paper/2306.07005/) (2023)
- [Testing Human Ability To Detect Deepfake Images of Human Faces](https://mlsanity.com/paper/2212.05056/) (2022)
- [Characterizing Photorealism and Artifacts in Diffusion Model-Generated Images](https://mlsanity.com/paper/2502.11989/) (2025)
- [How to Distinguish AI-Generated Images from Authentic Photographs](https://mlsanity.com/paper/2406.08651/) (2024)
- [How good are humans at detecting AI-generated images? Learnings from an experiment](https://mlsanity.com/paper/2507.18640/) (2025)
- [The Effect of Education in Prompt Engineering: Evidence from Journalists](https://mlsanity.com/paper/2409.12320/) (2024)
- [Partisan Fact-Checkers' Warnings Can Effectively Correct Individuals' Misbeliefs About Political Misinformation](https://mlsanity.com/paper/2505.08048/) (2025)
- [Designing Effective Digital Literacy Interventions for Boosting Deepfake Discernment](https://mlsanity.com/paper/2507.23492/) (2025)

## Abstract (arXiv)

Across social and online platforms, people are increasingly exposed to AI-generated images. As a consequence, the task of distinguishing AI-generated from authentic images is becoming a central challenge for information ecosystems. While humans perform better than chance, accuracy falls short of many operational needs. Initial evidence shows that visually oriented training can improve deepfake detection but does not improve participants' ability to identify real images as real. Here, we investigate the efficacy of a brief training intervention for intelligence analysts employed by the United States government in 2024. We conducted a counterbalanced within-subject randomized experiment in which we showed participants real and AI-generated images varying in pose complexity and scene context and asked them whether each image was real or AI-generated, both before and after an expert delivered a 30-minute training that pointed out patterns in seven real and 50 AI-generated images. We collected 2,544 image-level judgments from 32 intelligence analysts. We find training increased overall accuracy by 9 percentage points (95% CI: [2.7, 15.4]) from a baseline of 72%. We find the improvement is driven by a 14.2 percentage point increase in accuracy for real images (95% CI: [0.7, 27.7]). Through a careful experimental setup that curated matched pairs of real and AI-generated images across pose complexity categories, we reveal how these trainings influence people with different levels of digital forensics and generative AI experience and identify the kind of image-based content where this training intervention appears to be most effective. Ultimately, these results provide causal evidence that a brief, structured training can improve human judgment across a diverse array of real and AI-generated images, informing organizational responses to AI-generated visual misinformation.