Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2502.04364 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912222643486720 |
|---|---|
| author | You, Wenhao Hooi, Bryan Wang, Yiwei Choo, Euijin Yang, Ming-Hsuan Yuan, Junsong Huang, Zi Cai, Yujun |
| author_facet | You, Wenhao Hooi, Bryan Wang, Yiwei Choo, Euijin Yang, Ming-Hsuan Yuan, Junsong Huang, Zi Cai, Yujun |
| contents | Recent advancements in diffusion models have driven the growth of text-guided image editing tools, enabling precise and iterative modifications of synthesized content. However, as these tools become increasingly accessible, they also introduce significant risks of misuse, emphasizing the critical need for robust attribution methods to ensure content authenticity and traceability. Despite the creative potential of such tools, they pose significant challenges for attribution, particularly in adversarial settings where edits can be layered to obscure an image's origins. We propose LambdaTracer, a novel latent-space attribution method that robustly identifies and differentiates authentic outputs from manipulated ones without requiring any modifications to generative or editing pipelines. By adaptively calibrating reconstruction losses, LambdaTracer remains effective across diverse iterative editing processes, whether automated through text-guided editing tools such as InstructPix2Pix and ControlNet or performed manually with editing software such as Adobe Photoshop. Extensive experiments reveal that our method consistently outperforms baseline approaches in distinguishing maliciously edited images, providing a practical solution to safeguard ownership, creativity, and credibility in the open, fast-evolving AI ecosystems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lost in Edits? A $λ$-Compass for AIGC Provenance You, Wenhao Hooi, Bryan Wang, Yiwei Choo, Euijin Yang, Ming-Hsuan Yuan, Junsong Huang, Zi Cai, Yujun Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Machine Learning Recent advancements in diffusion models have driven the growth of text-guided image editing tools, enabling precise and iterative modifications of synthesized content. However, as these tools become increasingly accessible, they also introduce significant risks of misuse, emphasizing the critical need for robust attribution methods to ensure content authenticity and traceability. Despite the creative potential of such tools, they pose significant challenges for attribution, particularly in adversarial settings where edits can be layered to obscure an image's origins. We propose LambdaTracer, a novel latent-space attribution method that robustly identifies and differentiates authentic outputs from manipulated ones without requiring any modifications to generative or editing pipelines. By adaptively calibrating reconstruction losses, LambdaTracer remains effective across diverse iterative editing processes, whether automated through text-guided editing tools such as InstructPix2Pix and ControlNet or performed manually with editing software such as Adobe Photoshop. Extensive experiments reveal that our method consistently outperforms baseline approaches in distinguishing maliciously edited images, providing a practical solution to safeguard ownership, creativity, and credibility in the open, fast-evolving AI ecosystems. |
| title | Lost in Edits? A $λ$-Compass for AIGC Provenance |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2502.04364 |