Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.25009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916043097636864 |
|---|---|
| author | Cao, Huangsen Chu, Hongkang Li, Yuxi Zhang, Ying Li, Chen Lyu, Jing Wang, Yongwei Zhao, Yu Wu, Fei |
| author_facet | Cao, Huangsen Chu, Hongkang Li, Yuxi Zhang, Ying Li, Chen Lyu, Jing Wang, Yongwei Zhao, Yu Wu, Fei |
| contents | The rapid advancement of generative models has made synthetic images increasingly realistic, challenging reliable detection. Existing methods are often limited to end-to-end classification or monolithic reasoning, and thus fail to model structured forensic reasoning and heterogeneous visual evidence. We revisit synthetic image detection from a cognitive perspective and propose a \textit{Heuristic-to-Reasoning} cognitive skill learning framework for evidence-based forensic analysis. Given an input image, our framework first extracts heuristic perceptual clues, selects the optimal forensic skill, and then performs skill-conditioned reasoning for evidence extraction and decision making. To support this paradigm, we introduce \textbf{ClueAegis-Bench}, which decomposes synthetic image detection into explicitly annotated forensic cognitive skills for structured evaluation beyond binary classification. Based on this benchmark, we propose \textbf{ClueAegis} (\underline{C}ognitive-skill \underline{L}earning for \underline{U}nified \underline{E}vidence-based Synthetic Image Detection), a two-stage agentic framework that conducts heuristic skill selection followed by evidence-guided reasoning through skill-conditioned toolchains. This design reformulates synthetic image detection as a configurable multi-skill reasoning process that bridges perception, skill selection, and forensic reasoning. Extensive experiments show that ClueAegis achieves state-of-the-art performance while improving cross-domain generalization and robustness. It also provides transparent reasoning trajectories and structured forensic evidence, offering a more explainable alternative to conventional end-to-end detectors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25009 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ClueAegis: Heuristic-to-Reasoning Cognitive-skill Learning for Unified Evidence-based Synthetic Image Detection Cao, Huangsen Chu, Hongkang Li, Yuxi Zhang, Ying Li, Chen Lyu, Jing Wang, Yongwei Zhao, Yu Wu, Fei Computer Vision and Pattern Recognition The rapid advancement of generative models has made synthetic images increasingly realistic, challenging reliable detection. Existing methods are often limited to end-to-end classification or monolithic reasoning, and thus fail to model structured forensic reasoning and heterogeneous visual evidence. We revisit synthetic image detection from a cognitive perspective and propose a \textit{Heuristic-to-Reasoning} cognitive skill learning framework for evidence-based forensic analysis. Given an input image, our framework first extracts heuristic perceptual clues, selects the optimal forensic skill, and then performs skill-conditioned reasoning for evidence extraction and decision making. To support this paradigm, we introduce \textbf{ClueAegis-Bench}, which decomposes synthetic image detection into explicitly annotated forensic cognitive skills for structured evaluation beyond binary classification. Based on this benchmark, we propose \textbf{ClueAegis} (\underline{C}ognitive-skill \underline{L}earning for \underline{U}nified \underline{E}vidence-based Synthetic Image Detection), a two-stage agentic framework that conducts heuristic skill selection followed by evidence-guided reasoning through skill-conditioned toolchains. This design reformulates synthetic image detection as a configurable multi-skill reasoning process that bridges perception, skill selection, and forensic reasoning. Extensive experiments show that ClueAegis achieves state-of-the-art performance while improving cross-domain generalization and robustness. It also provides transparent reasoning trajectories and structured forensic evidence, offering a more explainable alternative to conventional end-to-end detectors. |
| title | ClueAegis: Heuristic-to-Reasoning Cognitive-skill Learning for Unified Evidence-based Synthetic Image Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.25009 |