arXiv:2511.02791v1 Announce Type: new 
Abstract: The threats posed by AI-generated media, particularly deepfakes, are now raising significant challenges for multimedia forensics, misinformation detection, and biometric system resulting in erosion of public trust in the legal system, significant increase in frauds, and social engineering attacks. Although several forensic methods have been proposed, they suffer from three critical gaps: (i) use of non-standardized benchmarks with GAN- or diffusion-generated images, (ii) inconsistent training protocols (e.g., scratch, frozen, fine-tuning), and (iii) limited evaluation metrics that fail to capture generalization and explainability. These limitations hinder fair comparison, obscure true robustness, and restrict deployment in security-critical applications. This paper introduces a unified benchmarking framework for systematic evaluation of forensic methods under controlled and reproducible conditions. We benchmark ten SoTA forensic methods (scratch, frozen, and fine-tuned) and seven publicly available datasets (GAN and diffusion) to perform extensive and systematic evaluations. We evaluate performance using multiple metrics, including accuracy, average precision, ROC-AUC, error rate, and class-wise sensitivity. We also further analyze model interpretability using confidence curves and Grad-CAM heatmaps. Our evaluations demonstrate substantial variability in generalization, with certain methods exhibiting strong in-distribution performance but degraded cross-model transferability. This study aims to guide the research community toward a deeper understanding of the strengths and limitations of current forensic approaches, and to inspire the development of more robust, generalizable, and explainable solutions.

تسلط دراسة حديثة الضوء على التحديات التي تطرحها الوسائط التي تم إنشاؤها بواسطة الذكاء الاصطناعي، وخاصة الصور المزيفة، والتي تهدد الطب الشرعي متعدد الوسائط وثقة الجمهور. على الرغم من وجود طرق جنائية مختلفة، إلا أنها تواجه فجوات كبيرة، بما في ذلك نقص المعايير الموحدة. تهدف هذه الدراسة إلى معالجة هذه القضايا واستكشاف اتجاهات مستقبلية لمكافحة المعلومات المضللة والاحتيال.

Un estudio reciente destaca los desafíos que plantean los medios generados por IA, especialmente los deepfakes, que amenazan la forensía multimedia y la confianza pública. Aunque existen varios métodos forenses, enfrentan importantes brechas, incluida la falta de estándares normalizados. Esta investigación tiene como objetivo abordar estos problemas y explorar futuras direcciones para combatir la desinformación y el fraude.

Une étude récente met en lumière les défis posés par les médias générés par l'IA, en particulier les deepfakes, qui menacent la criminalistique multimédia et la confiance du public. Bien que diverses méthodes d'analyse existent, elles présentent des lacunes importantes, notamment l'absence de normes standardisées. Cette recherche vise à aborder ces problèmes et à explorer les futures directions pour lutter contre la désinformation et la fraude.

A recent study highlights the challenges posed by AI-generated media, especially deepfakes, which threaten multimedia forensics and public trust. While various forensic methods exist, they face significant gaps, including the lack of standardized benchmarks. This research aims to address these issues and explore future directions in combating misinformation and fraud.

AI-Generated Image Detection: An Empirical Study and Future Research Directions

arXiv:2506.10016v3 Announce Type: replace-cross 
Abstract: Multimodal Generative Models (MGMs) have rapidly evolved beyond text generation, now spanning diverse output modalities including images, music, video, human motion, and 3D objects, by integrating language with other sensory modalities under unified architectures. This survey categorises six primary generative modalities and examines how foundational techniques, namely Self-Supervised Learning (SSL), Mixture of Experts (MoE), Reinforcement Learning from Human Feedback (RLHF), and Chain-of-Thought (CoT) prompting, enable cross-modal capabilities. We analyze key models, architectural trends, and emergent cross-modal synergies, while highlighting transferable techniques and unresolved challenges. Building on a common taxonomy of models and training recipes, we propose a unified evaluation framework centred on faithfulness, compositionality, and robustness, and synthesise evidence from benchmarks and human studies across modalities. We further analyse trustworthiness, safety, and ethical risks, including multimodal bias, privacy leakage, and the misuse of high-fidelity media generation for deepfakes, disinformation, and copyright infringement in music and 3D assets, together with emerging mitigation strategies. Finally, we discuss how architectural trends, evaluation protocols, and governance mechanisms can be co-designed to close current capability and safety gaps, outlining critical paths toward more general-purpose, controllable, and accountable multimodal generative systems.

تم نشر مسح شامل حول النماذج التوليدية متعددة الوسائط (MGM)، يوضح تطورها من توليد النصوص إلى مجموعة متنوعة من أنماط الإخراج مثل الصور والموسيقى والفيديو. تصنف الدراسة ستة أنماط توليدية رئيسية وتناقش تقنيات أساسية مثل التعلم الذاتي والإشراف والتفكير المتسلسل التي تمكن من القدرات عبر الوسائط.

Se ha publicado una encuesta completa sobre los Modelos Generativos Multimodales (MGM), que detalla su evolución de la generación de texto a diversas modalidades de salida como imágenes, música y video. El estudio categoriza seis modalidades generativas principales y discute técnicas fundamentales como el Aprendizaje Auto-Supervisado y el razonamiento por Cadena de Pensamientos que permiten capacidades intermodales.

Une enquête complète sur les Modèles Génératifs Multimodaux (MGM) a été publiée, détaillant leur évolution de la génération de texte à diverses modalités de sortie telles que les images, la musique et la vidéo. L'étude catégorise six modalités génératives principales et discute des techniques fondamentales comme l'Apprentissage Auto-Supervisé et le raisonnement par Chaîne de Pensées qui permettent des capacités intermodales.

A comprehensive survey on Multimodal Generative Models (MGMs) has been published, detailing their evolution from text generation to various output modalities such as images, music, and video. The study categorizes six primary generative modalities and discusses foundational techniques like Self-Supervised Learning and Chain-of-Thought prompting that enable cross-modal capabilities.

AI-Generated Image Detection: An Empirical Study and Future Research Directions

Was this article worth reading? Share it

Republiclabs.ai

Video Face Swap AI — Discover what people think of this product.

GPTHumanizer