analiza aiqbench
This research introduces a self-referential retrosynthesis framework that verifies the provenance of synthetic media without altering generator architectures or requiring watermark embedding. By leveraging an encoder-decoder pair for round-trip consistency checks, the method provides interpretable evidence to determine if content originates from specific generative models under a fixed-generator setting. The approach offers a practical solution for explainable forensics in an era where modifying MLaaS platforms is often impractical.
Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics
arXiv:2609.02268v1 Announce Type: cross Abstract: 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.
Abstract: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.
12 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
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
arXiv:2609.02268 [cs.CR]
(or arXiv:2609.02268v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2609.02268 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 235 cuvinte
Subiecte conexe
Artmarket.com: H1 2026 Financial Report -- One-of-a - Kind AI Systems Intuitive Artmarket and Blind Spot Will Drive the Next Phase of Growth for
australiannews.net · 29 sept. 2026
Artmarket.com: H1 2026 Financial Report -- One-of-a - Kind AI Systems Intuitive Artmarket® and Blind Spot Will Drive the Next Phase of Growth for AI - First Artprice in 2026 - 2030
thailand-business-news.com · 28 sept. 2026
Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks
arXiv · 9 iun. 2026
Auditable Climate Risk Intelligence from Fragmented ESG Data: Deterministic Orchestration and Imbalance-Aware Learning for Scope 1-3 Validation
arXiv · 3 iun. 2026