AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images
Open Access
- 30 September 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 513-530
Abstract
Recent advances in the field of generative artificial intelligence (AI) have blurred the lines between authentic and machine-generated content, making it almost impossible for humans to distinguish between such media. One notable consequence is the use of AI-generated images for fake profiles on social media. While several types of disinformation campaigns and similar incidents have been reported in the past, a systematic analysis has been lacking. In this work, we conduct the first large-scale investigation of the prevalence of AI-generated profile pictures on Twitter. We tackle the challenges of a real-world measurement study by carefully integrating various data sources and designing a multi-stage detection pipeline. Our analysis of nearly 15 million Twitter profile pictures shows that Math 1 were artificially generated, confirming their notable presence on the platform. We comprehensively examine the characteristics of these accounts and their tweet content, and uncover patterns of coordinated inauthentic behavior. The results also reveal several motives, including spamming and political amplification campaigns. Our research reaffirms the need for effective detection and mitigation strategies to cope with the potential negative effects of generative AI in the future.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft (EXC 2092 CASA - 390781972)
- Leibniz Association Competition (P101/2020)
This publication has 28 references indexed in Scilit:
- Towards Universal Fake Image Detectors that Generalize Across Generative Models2023
- Scaling up GANs for Text-to-Image Synthesis2023
- A Study of the Human Perception of Synthetic Faces2021
- A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection2021
- Charting the Landscape of Online Cryptocurrency ManipulationIEEE Access, 2020
- Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions2020
- CNN-Generated Images Are Surprisingly Easy to Spot… for Now2020
- A Style-Based Generator Architecture for Generative Adversarial Networks2019
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015