Search papers, labs, and topics across Lattice.
This study introduces a self-referential retrosynthesis framework designed for explainable AI provenance forensics, enabling reliable tracing of synthetic media generated by fixed models. By employing a jointly optimized encoder-decoder pair, the framework achieves round-trip consistency verification without altering the generator's architecture or parameters. Experimental results demonstrate that the resynthesized images maintain high visual fidelity and effectively trace back to their original inputs, providing interpretable evidence for content provenance.
Tracing the origins of synthetic media is now possible without altering generator architectures, thanks to a novel self-referential framework that ensures round-trip consistency.
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.
