Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914466441986048 |
|---|---|
| author | Guan, Xinlei Arosemena, David Dhandu, Tejaswi Huang, Kuan Xu, Meng Li, Miles Q. Shen, Bingyu Qin, Ruiyang Tida, Umamaheswara Rao Li, Boyang |
| author_facet | Guan, Xinlei Arosemena, David Dhandu, Tejaswi Huang, Kuan Xu, Meng Li, Miles Q. Shen, Bingyu Qin, Ruiyang Tida, Umamaheswara Rao Li, Boyang |
| contents | The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images can be paired with harmful or misleading text, creating difficult-to-detect misuse. This contextual misuse undermines the traditional moderation framework and complicates attribution, as synthetic images typically lack persistent metadata or device signatures. We introduce a steganography enabled attribution framework that embeds cryptographically signed identifiers into images at creation time and uses multimodal harmful content detection as a trigger for attribution verification. Our system evaluates five watermarking methods across spatial, frequency, and wavelet domains. It also integrates a CLIP-based fusion model for multimodal harmful-content detection. Experiments demonstrate that spread-spectrum watermarking, especially in the wavelet domain, provides strong robustness under blur distortions, and our multimodal fusion detector achieves an AUC-ROC of 0.99, enabling reliable cross-modal attribution verification. These components form an end-to-end forensic pipeline that enables reliable tracing of harmful deployments of AI-generated imagery, supporting accountability in modern synthetic media environments. Our code is available at GitHub: https://github.com/bli1/steganography |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10460 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection Guan, Xinlei Arosemena, David Dhandu, Tejaswi Huang, Kuan Xu, Meng Li, Miles Q. Shen, Bingyu Qin, Ruiyang Tida, Umamaheswara Rao Li, Boyang Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security Emerging Technologies The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images can be paired with harmful or misleading text, creating difficult-to-detect misuse. This contextual misuse undermines the traditional moderation framework and complicates attribution, as synthetic images typically lack persistent metadata or device signatures. We introduce a steganography enabled attribution framework that embeds cryptographically signed identifiers into images at creation time and uses multimodal harmful content detection as a trigger for attribution verification. Our system evaluates five watermarking methods across spatial, frequency, and wavelet domains. It also integrates a CLIP-based fusion model for multimodal harmful-content detection. Experiments demonstrate that spread-spectrum watermarking, especially in the wavelet domain, provides strong robustness under blur distortions, and our multimodal fusion detector achieves an AUC-ROC of 0.99, enabling reliable cross-modal attribution verification. These components form an end-to-end forensic pipeline that enables reliable tracing of harmful deployments of AI-generated imagery, supporting accountability in modern synthetic media environments. Our code is available at GitHub: https://github.com/bli1/steganography |
| title | Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security Emerging Technologies |
| url | https://arxiv.org/abs/2604.10460 |