Work

A Statistical Image Realism Score For Deepfake Detection

Year: 2024

Type: conference-paper

Abstract: Recent advances in generative visual content have led to a quantum leap in the quality of artificially generated Deepfake content. Especially, diffusion models are causing growing concerns among communities due to their ever-increasing realism. However, quantifying the realism of generated content is still challenging. Existing evaluation metrics, such as Inception Score and Fréchet inception distance, fall short on benchmarking diffusion models due to the versatility of the generated images. To address this, we propose the Image Realism Score (IRS) evaluation metric, computed from five statistical measures of a given image. This non-learning-based metric not only efficiently quantifies the realism of generated images, but it is also a viable tool for detecting if an image is real or fake. We experimentally establish the model- and data-agnostic nature of the proposed IRS by successfully detecting fake images generated by Stable Diffusion Model (SDM), Dalle2, Dalle3, Deepfloyd, Kandinsky, Midjourney and BigGAN.

Source: Proceedings - International Conference on Image Processing

DOI: 10.1109/icip51287.2024.10648084

Authors: Yunzhuo Chen, Naveed Akhtar, Nur Al Hasan Haldar, Jordan Vice, Ajmal Mian

Institutions: The University of Western Australia, The University of Melbourne

Language: English

Topic: Digital Media Forensic Detection

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Australian Government, Australian Research Council

Awards: G2330925116, G3206439402