LiteUpdate: A Lightweight Framework for Updating AI-Generated Image Detectors

TL;DR

LiteUpdate is a lightweight, efficient framework that improves AI-generated image detectors by selecting boundary samples and merging model weights, effectively adapting to new generators while reducing forgetting.

Contribution

It introduces a novel sample selection and model merging approach to enhance detector update efficiency and robustness against catastrophic forgetting.

Findings

Significantly improved detection accuracy on Midjourney from 87.63% to 93.03%.

Enhanced detector adaptability to new generative models.

Reduced catastrophic forgetting in detector updates.

Abstract

The rapid progress of generative AI has led to the emergence of new generative models, while existing detection methods struggle to keep pace, resulting in significant degradation in the detection performance. This highlights the urgent need for continuously updating AI-generated image detectors to adapt to new generators. To overcome low efficiency and catastrophic forgetting in detector updates, we propose LiteUpdate, a lightweight framework for updating AI-generated image detectors. LiteUpdate employs a representative sample selection module that leverages image confidence and gradient-based discriminative features to precisely select boundary samples. This approach improves learning and detection accuracy on new distributions with limited generated images, significantly enhancing detector update efficiency. Additionally, LiteUpdate incorporates a model merging module that fuses weights from multiple fine-tuning trajectories, including pre-trained, representative, and random updates. This balances the adaptability to new generators and mitigates the catastrophic forgetting of prior knowledge. Experiments demonstrate that LiteUpdate substantially boosts detection performance in various detectors. Specifically, on AIDE, the average detection accuracy on Midjourney improved from 87.63% to 93.03%, a 6.16% relative increase.