轻量更新框架，让图像检测器快速适应新生成模型。
LiteUpdate: A Lightweight Framework for Updating AI-Generated Image Detectors
- 选关键样本+融合多路径权重，高效更新检测器。
- 对Midjourney生成图检测准确率提升6.16%至93.03%。
- 适合需要持续迭代的AI内容安全系统使用。
生成式AI快速发展催生了新型生成模型，但现有检测方法难以跟上，导致检测性能显著下降。为应对更新效率低和灾难性遗忘问题，本文提出LiteUpdate——一种轻量级检测器更新框架。该框架通过基于置信度与梯度判别特征的代表性样本选择模块，精准筛选边界样本，在有限生成图像下提升学习与检测精度，显著提高更新效率。同时引入模型融合模块，整合预训练、代表性及随机微调路径的权重，平衡对新生成器的适应能力并缓解先验知识遗忘。实验表明，LiteUpdate在多种检测器上均显著提升性能。以AIDE数据集为例，对Midjourney生成图像的平均检测准确率从87.63%提升至93.03%，相对增长6.16%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。