LEGO：用于合成图像检测的基于LoRA的面向生成器框架
LEGO: LoRA-Enabled Generator-Oriented Framework for Synthetic Image Detection
AI总结：
针对生成技术使合成图像难辨真伪，现有检测方法存在泛化和过拟合问题，提出LEGO框架。通过MLP调制多个LoRA模块，分两阶段训练，能提取特定生成器独特伪影，在少数据和少轮次训练下性能优于现有方法。
摘要：
生成技术的快速发展使得合成图像几乎与真实图像难以区分，因此迫切需要强大的检测器来应对错误信息。现有方法主要依赖于多个生成器共享的通用伪影特征，但随着生成器多样性增加，这些共同特征的重叠逐渐减少，严重损害模型泛化能力，而仅关注独特伪影又易导致过拟合。为此提出LEGO框架，其核心机制是用MLP调制多个LoRA模块，各模块预训练以捕获特定生成器的独特伪影，再进行基于注意力的特征融合。LEGO将训练过程分为两个阶段，把独特伪影提取委托给专门的LoRA模块。每个LoRA模块在单生成器数据集上单独训练以学习特定生成器表示，然后MLP和注意力层在混合数据集上训练以动态调节各模块贡献。受益于模块化且强大的设计，LEGO可通过纳入新的LoRA模块自然扩展以适应新出现的下一代数据集，在训练图像数量少、训练数据占比低且训练轮次少的情况下，仍比现有最优方法性能大幅提升。
英文摘要：
The rapid advancement of generative technologies has made synthetic images nearly indistinguishable from real ones, thereby creating an urgent need for robust detectors to counter misinformation. However, existing methods mainly rely on universal artifact features that are shared across multiple generators. We observe that as the diversity of generators increases, the overlap of these common features gradually decreases. This severely undermines model generalization. In contrast, focusing only on unique artifacts tends to cause overfitting to specific forgery patterns. To address this challenge, we propose LEGO (LoRA-Enabled Generator-Oriented Framework). The core mechanism of LEGO employs an MLP to modulate multiple LoRA (Low-Rank Adaptation) blocks, each pretrained to capture the unique artifacts of a specific generator, followed by attention-based feature fusion. Unlike conventional methods that seek a single universal solution, LEGO delegates unique artifact extraction to specialized LoRA modules by dividing its training procedure into two stages. Each LoRA module is individually trained on a single-generator dataset to learn generator-specific representations, then MLP and attention layers are trained on mixed datasets to dynamically regulate the contribution of each module. Benefiting from its modular yet robust design, LEGO can be naturally extended by incorporating new LoRA modules for adaptation to newly emerging next-generation datasets, while still achieving substantially better performance than prior SOTA methods with fewer than 30,000 training images, less than 10% of their training data, and only 5 epochs in each training stage.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
