{"ID":2832504,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.05590","arxiv_id":"2512.05590","title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","abstract":"The rapid advancement of generative models, particularly diffusion-based methods, has significantly improved the realism of synthetic images. As new generative models continuously emerge, detecting generated images remains a critical challenge. While fully supervised, and few-shot methods have been proposed, maintaining an updated dataset is time-consuming and challenging. Consequently, zero-shot methods have gained increasing attention in recent years. We find that existing zero-shot methods often struggle to adapt to specific image domains, such as artistic images, limiting their real-world applicability. In this work, we introduce CLIDE, a novel zero-shot detection method based on conditional likelihood approximation. Our approach computes likelihoods conditioned on real images, enabling adaptation across diverse image domains. We extensively evaluate CLIDE, demonstrating SOTA performance on a large-scale general dataset and significantly outperform existing methods in domain-specific cases. These results demonstrate the robustness of our method and underscore the need of broad, domain-aware generalization for the AI-generated image detection task. Code is available at https://tinyurl.com/clide-detector.","short_abstract":"The rapid advancement of generative models, particularly diffusion-based methods, has significantly improved the realism of synthetic images. As new generative models continuously emerge, detecting generated images remains a critical challenge. While fully supervised, and few-shot methods have been proposed, maintainin...","url_abs":"https://arxiv.org/abs/2512.05590","url_pdf":"https://arxiv.org/pdf/2512.05590v2","authors":"[\"Roy Betser\",\"Omer Hofman\",\"Roman Vainshtein\",\"Guy Gilboa\"]","published":"2025-12-05T10:25:58Z","proceeding":"eess.IV","tasks":"[\"eess.IV\"]","methods":"[\"Diffusion Model\"]","project_urls":"[\"https://tinyurl.com/clide-detector\"]","has_code":false,"code_links":[{"ID":606236,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/FujitsuResearch/domain-adaptive-image-detection","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606237,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/FujitsuResearch/domain-adaptive-image-detection.git","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606238,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/features/copilot","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606239,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/features/spark","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606240,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/features/models","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606241,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/features/actions","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606242,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/features/codespaces","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606243,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/features/issues","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606244,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/features/code-review","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606245,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/security/advanced-security","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606246,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/enterprise/startups","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606247,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/solutions/industry","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606248,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832504,"paper_url":"https://arxiv.org/abs/2512.05590","paper_title":"General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood","repo_url":"https://github.com/solutions/use-case","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}