EvoKnow：面向AI生成图像检测的持续知识演化

中文摘要 AI 辅助

AI生成图像检测器通常在固定的生成器域上训练，随着新生成模型的出现，其维护变得困难。持续自适应具有挑战性，因为重放历史生成图像成本高昂，而使用有限的当前域数据更新共享参数会覆盖先前的取证知识。我们提出EvoKnow，这是一个无重放框架，将持续AI生成图像检测表述为取证知识演化。EvoKnow保留从基础域学习到的共享取证基础，逐步添加孤立的残差专家以补充与生成器相关的证据，并通过分析增量路由器（AIR）检索专业知识，AIR从当前阶段生成图像和累积的充分统计量以闭式形式更新。实验表明，该方法具有有效的跨生成器泛化、少样本扩展和长程持续自适应能力。在每个新生成器到达时仅使用10张生成图像的情况下，EvoKnow在非基础GenImage生成器上实现96.70%的平均准确率，在Chameleon上实现94.48%的准确率（无需目标基准自适应）。在严格的无重放持续学习协议下，EvoKnow实现了最先进的持续学习性能，达到96.32%的平均阶段准确率和4.32%的平均遗忘率。

英文摘要

AI-generated image detectors are commonly trained on fixed generator domains and become difficult to maintain as new generative models emerge. Continual adaptation is challenging because replaying historical generated images is costly, whereas updating shared parameters with limited current-domain data can overwrite prior forensic knowledge. We propose EvoKnow, a replay-free framework that formulates continual AI-generated image detection as forensic knowledge evolution. EvoKnow preserves a shared forensic basis learned from base domains, incrementally adds isolated residual experts for complementary generator-relevant evidence, and retrieves expertise through an Analytical Incremental Router (AIR) updated in closed form from current-stage generated images and accumulated sufficient statistics. Experiments demonstrate effective cross-generator generalization, few-shot expansion, and long-horizon continual adaptation. With ten generated images per arriving generator, EvoKnow achieves 96.70% average accuracy on non-base GenImage generators and 94.48% accuracy on Chameleon without target-benchmark adaptation. Under a strict replay-free continual learning protocol, EvoKnow achieves state-of-the-art continual learning performance, attaining 96.32% mean stage-wise accuracy and 4.32% average forgetting.

发表机构

• Xiaohongshu Inc.（小红书科技有限公司）
• Southeast University（东南大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

19 pages, 6 figures