发表机构
Feng Chia University; National Institute of Informatics; University of Tokyo; Peking University（逢甲大学; 国立信息学研究所; 东京大学; 北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对MLaaS平台合成媒体来源追踪难题，提出固定生成器下的自引用逆合成框架，通过编码器-解码器对实现往返一致性验证，无需水印或修改生成过程，可可靠追踪生成式内容来源并提供可解释证据。
AI 中文摘要
随着机器学习即服务（MLaaS）平台上生成式模型的快速普及，在不修改生成器架构或参数的情况下可靠追踪合成媒体的来源仍是一项重大挑战。本研究在固定生成器设置下，提出一种用于可解释AI来源取证的自引用逆合成框架。该框架利用联合优化的编码器-解码器对实现自嵌入机制，支持往返一致性验证。推理阶段，客户端输入先被编码，再经生成器处理以生成具有高视觉保真度的输出；取证验证时，通过分析重合成图像与查询图像的一致性，判断该图像是否源自目标生成式模型。本方法无需嵌入水印或修改生成过程。实验结果表明，从编码输入生成的图像视觉质量与原始生成器输出相当，而解码图像可可靠回溯至对应源输入；此外，该框架为生成式内容来源提供可解释证据，为可解释生成式AI取证建立了实用工具。
英文摘要
With the rapid proliferation of generative models on Machine Learning as a Service (MLaaS) platforms, reliably tracing the provenance of synthetic media without modifying generator architectures or parameters remains a major challenge. In this work, we propose a self-referential retrosynthesis framework for explainable AI provenance forensics under a fixed-generator setting. The framework leverages a jointly optimized encoder-decoder pair to implement a self-embedding mechanism that enables round-trip consistency verification. During inference, client inputs are first encoded and then processed by the generator to produce outputs with high visual fidelity. For forensic verification, the consistency between the resynthesized image and the query image is analyzed to determine whether the image originates from the target generative model. Our approach eliminates the need for watermark embedding or modifications to the generation process. Experimental results show that images generated from encoded inputs maintain visual quality comparable to original generator outputs, while decoded images reliably trace back to their corresponding source inputs. Furthermore, the framework provides interpretable evidence for generative content provenance, establishing a practical tool for explainable generative AI forensics.
Comments12 pages, 10 figures. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
