LiteUpdate: A Lightweight Framework for Updating AI-Generated Image Detectors
This addresses the need for continuously updating detectors to adapt to new AI image generators, which is an incremental improvement for the domain of AI-generated content detection.
The paper tackles the problem of AI-generated image detectors degrading as new generative models emerge, proposing LiteUpdate to efficiently update detectors with limited new data, resulting in a 6.16% relative increase in detection accuracy on Midjourney from 87.63% to 93.03%.
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.