Evolution of Detection Performance throughout the Online Lifespan of Synthetic Images
This addresses the challenge of maintaining detection accuracy for synthetic images in real-world online environments, which is incremental as it builds on existing methods with a specific enhancement.
The study tackled the problem of synthetic image detectors struggling with images that evolve online, finding that detection performance degrades over time, and demonstrated a retrieval-assisted approach that improved average detection efficacy by 6.7% in balanced accuracy and 7.8% in AUC.
Synthetic images disseminated online significantly differ from those used during the training and evaluation of the state-of-the-art detectors. In this work, we analyze the performance of synthetic image detectors as deceptive synthetic images evolve throughout their online lifespan. Our study reveals that, despite advancements in the field, current state-of-the-art detectors struggle to distinguish between synthetic and real images in the wild. Moreover, we show that the time elapsed since the initial online appearance of a synthetic image negatively affects the performance of most detectors. Ultimately, by employing a retrieval-assisted detection approach, we demonstrate the feasibility to maintain initial detection performance throughout the whole online lifespan of an image and enhance the average detection efficacy across several state-of-the-art detectors by 6.7% and 7.8% for balanced accuracy and AUC metrics, respectively.