Keywords
multi-agent systems
multimodal deep learning
visual forensics
explainable AI
image localization
Abstract
The rapid advancement of generative artificial intelligence has made image forgery more accessible and undetectable, posing significant threats to digital forensics, journalism integrity, and information security. Existing image forgery detection methods typically rely on single-modal forensic cues or monolithic deep neural networks, which struggle to generalize across diverse forgery types and fail to provide interpretable reasoning for their decisions. This paper proposes UniShield-MA, a multi-agent driven unified multi-modal framework that integrates forensic artifact analysis, semantic consistency verification, frequency domain inspection, and large language model reasoning into a collaborative agent architecture. The framework comprises four specialized perception agents and a central orchestrator agent that performs evidence aggregation, cross-agent debate, and adaptive confidence weighting. Extensive experiments on four benchmark datasets (CASIA v2, NIST16, Coverage, and IMG-Forensics-10K) demonstrate that UniShield-MA achieves 93.7% average forgery classification accuracy and 83.2% pixel-level localization IoU, outperforming state-of-the-art single-modality methods by 4.3-7.8 percentage points. Ablation studies confirm that each agent contributes uniquely to overall performance, and the cross-agent debate mechanism improves robustness against sophisticated forgery types by 6.1%. The proposed framework offers both high detection accuracy and interpretable multi-modal reasoning, addressing a critical gap in current image forensics practice.
References
Xu, Z., Zhang, X., Li, R., Tang, Z., Huang, Q., & Zhang, J. (2024). Fakeshield: Explainable image forgery detection and localization via multi-modal large language models. arXiv preprint arXiv:2410.02761.
Huang, Q., Xu, Z., Zhang, X., & Zhang, J. (2025). UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization. arXiv preprint arXiv:2510.03161.
Jia, Z., You, K., He, W., Tian, Y., Feng, Y., Wang, Y., ... & Zhang, Z. (2023). Event-based semantic segmentation with posterior attention. IEEE Transactions on Image Processing, 32, 1829-1842.
Lu, B., Li, D., Zhao, K., Ning, E., Gao, W., Dong, J., & Ning, X. (2026). Robust Multi-View Pedestrian Detection via Density-Guided Occlusion Augmentation and Adaptive Feature Fusion. Information Fusion, 104638.
Tan, Y., Cheng, X., Qin, Y., Li, Z., & Zhang, J. (2026). Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video. arXiv preprint arXiv:2603.13912.
Zhao, R., Zhou, L., Shang, Z., Liu, Y., Zhang, Y., Li, S., ... & Ning, X. (2026). ProMML for robust few-shot adaptation of vision-language models. Pattern Recognition, 114160.
Xu, Y., Sun, Y., Zhai, B., Li, M., Liang, W., Li, Y., & Du, S. (2025, April). Zero-shot video moment retrieval via off-the-shelf multimodal large language models. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 9, pp. 8978-8986).
Wang, T., & Xia, Z. (2025). Stability of In-Context Learning: A Spectral Coverage Perspective. arXiv preprint arXiv:2509.20677.
Huang, C., Jia, Z., Fei, H., Zhu, Y., Yuan, Z., Zhang, J., & Zhou, J. (2025, October). ArtFRD: A Fisher-Rao Mixture Metric for Generative Model Aesthetic Evaluation. In Proceedings of the 33rd ACM International Conference on Multimedia (pp. 6654-6662).
Lyu, M., Guo, J., Gao, W., & Lyu, T. (2026). Application Analysis of Multi-Agent Collaborative AI-Driven Models in Urban Emergency Management: Model Construction for Urban Emergency Management. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-26.
Zhang, D., Sang, C., & Lyu, T. (2026). Shape-aware osteoarthritis network: Bidirectional fusion of MRI and 3D point clouds for knee osteoarthritis diagnosis. Information Fusion, 104198.
Zheng, X., Chen, X., Gong, S., Griffin, X., & Slabaugh, G. (2025, September). Xfmamba: Cross-fusion mamba for multi-view medical image classification. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 672-682). Cham: Springer Nature Switzerland.
Dong, J., Shen, Z., Luo, H., Lyu, T., & Gao, W. (2026). Graph attention and text semantics improve personalized recommendation. Scientific Reports.
Cheng, X., Qin, Y., Tan, Y., Li, Z., Wang, Y., Xiao, H., & Zhang, Y. (2026). Psymem: Fine-grained psychological alignment and explicit memory control for advanced role-playing llms. Transactions of the Association for Computational Linguistics, 14, 510-529.
Mini Han Wang , " AI-Powered Innovations in Ophthalmic Diagnosis and Treatment ", Bentham Science Publishers (2025). [http://dx.doi.org/10.2174/97988988122871250101](http://dx.doi.org/10.2174/97988988122871250101)
Ye, Z., Xiao, X., & Wang, H. (2024, July). Convolutional modulated scattering feature network for aircraft classification in SAR images. In IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium (pp. 9329-9332). IEEE.
Lan, J., Ye, Z., Li, R., Qiu, K., Li, P., Guo, X., & Hu, F. (2026). A Multi-Level Cross-Modal Edge Filtering Method for High-Resolution Optical-SAR Image Registration. Remote Sensing, 18(11), 1741.
Li, P., Ye, Z., & Wang, H. (2026, May). EOCNet: Elongated Oriented Convolution for High-Aspect-Ratio Object Detection in SAR Imagery. In 2026 China Aerospace Information Technology Conference (CAIT) (pp. 1-4). IEEE.
Zhang, Y., Yang, Z., Chen, J., Qi, Z., & Yang, G. (2019, August). Presentation, derivation and numerical experiments of a group of extrapolation formulas. In 2019 9th International Conference on Information Science and Technology (ICIST) (pp. 240-246). IEEE.
Lv, Z., Wang, Q., Lyu, T., & Dong, J. (2026). A Deep Learning-Based Model for User Emotion Recognition and Behavior Guidance Design: EMoGuideNet-An Emotion-Aware Multimodal Framework for Enhancing Intelligent User Interaction. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-30.
Huang, T., Huang, C., Li, S., & Lyu, T. (2026). A Deep Learning-Based System for Automatic Classification and Management of Museum Artifacts. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-26.
Jiang, C. (2026). Information doesn’t work? Testing experiential drivers of VR application in heritage tourism by affective-cognitive pathways. Journal of Hospitality and Tourism Technology, 1-28.
Wang, X., Liu, S., Qi, Z., Zhou, L., & Cui, Q. (2025). Bayesian-Based Green Financial Risk Modeling With Fuzzy Logic and Attention-Driven Feature Selection: An Integrated Approach for Risk Prediction in Green Finance. Journal of Organizational and End User Computing (JOEUC), 37(1), 1-23.
Yan, Z., & Lyu, T. (2026). Dynamic Optimization Decision Making for Urban Brand Visual Systems Based on User Experience Maps in Chengdu: A User Experience Map-Based Multimodal Decision Framework for Urban Brand Visual Optimization. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-57.
Jia, J., & Zhou, L. (2025). A threat detection scheme for financial big data in internet of things. Frontiers in Physics, 13, 1633021.
Lv, Z., Wang, Q., Gao, W., & Zhou, L. (2026). Enhancing Corporate Green Innovation Under the Green Factory Policy: A Graph Neural Network Approach for Management Decision-Making. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-33.
Yu, Y., Kang, L., & Gao, W. (2026). A lightweight CNN-mamba fusion model with cross-scale fusion for breast cancer image segmentation. Ain Shams Engineering Journal, 17(12), 104470.
Wu, H., Song, Y., Zhang, Z., Zhang, Z., Zhou, H., Ma, W. Y., & Liu, J. (2026). Rationalized All-Atom Protein Design with Unified Multi-Modal Bayesian Flow. Advances in Neural Information Processing Systems, 38, 3019-3050.
Zhou, Y., Yao, J., Liu, Y., Dong, Z., Ye, W., Wen, J., & Choi, L. Y. (2026). Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity. arXiv preprint arXiv:2608.02665.
Chen, Q. (2026, March). RADR-MO: Resilience-Aware Dynamic Re-routing via Graph Attention Networks and Multi-Objective Meta-Reinforcement Learning for Supply Chain Resilience. In Proceedings of the 2026 3rd International Conference on Innovation Management and Information Systems (pp. 155-162).
Ma, Q., & Wu, R. (2026). When Validation Stops Learning: Auditing Update Admission for Continual Embodied Agents. arXiv preprint arXiv:2609.10873.
Que, H., Gao, H., Shan, W., Liu, M., An, J., Deng, F., ... & Mu, L. (2026). FM-SAM: individual tree crown delineation and classification based on Segmentation Anything Model (SAM) and YOLOv10 in UAV imagery for forest monitoring. Computers and Electronics in Agriculture, 240, 111162.
Zhu, H., Huang, X., Gao, H., Jiang, M., Que, H., & Mu, L. (2025, July). A Wireless Collaborated Inference Acceleration Framework for Plant Disease Recognition. In International Conference on Intelligent Computing (pp. 331-341). Singapore: Springer Nature Singapore.
Liu, M., Que, H., Yang, X., Zhang, K., Yu, Q., Yan, L., ... & Zhou, N. (2023). A Selective Bit Dropping and Encoding Co-Strategy in Image Processing for Low-Power Design in DRAM and SRAM. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 13(1), 48-57.
Gao, H., Que, H., Au, H., Shan, W., Liu, M., Qin, Y., ... & Qiao, F. (2025). SenseExpo: Efficient Autonomous Exploration with Prediction Information from Lightweight Neural Networks. arXiv preprint arXiv:2503.16000.
Xi, X., Chen, P., Qiu, Y., Luo, R., Tong, P., & Liang, J. Video-BCI: Bayesian Cognitive Integration of Self-Prior Hypotheses for Video Understanding. In Forty-third International Conference on Machine Learning.
Liang, J., Xiao, Y., Yang, H., Yu, Z., Liu, J. N., & Yang, K. (2026, April). C-HyPOD: Causal Hyperbolic Representation Learning with Prototype Orthogonal Disentanglement for Graph Out-of-Distribution Recommendation. In Proceedings of the ACM Web Conference 2026 (pp. 6541-6550).
C. Wan, Y. Luo, W. Wu, N. D. Hatziargyriou and S. Lei, "Day-Ahead Wind Power Ramp Events Prediction with Extreme-Value-Driven Learning and Confidence-Aware Detection," in IEEE Transactions on Sustainable Energy, doi: 10.1109/TSTE.2026.3669605.
Y. Wang, C. Wan and Y. Luo, "WeaGAN++: An Efficient Weather-Aware Graph Attention Network for Traffic Prediction," in IEEE Internet of Things Journal, vol. 13, no. 10, pp. 21197-21212, 15 May15, 2026, doi: 10.1109/JIOT.2026.3665116.
Quan, Q., Gao, Y., & Wang, Q. (2025). The impact of teacher emotional support on students' engagement in AI-mediated English learning environments: The mediating role of resilience and self-efficacy. Acta Psychologica, 260, 105766.
Yang, J., Li, Q., Yu, H., Wang, X., Wang, C., Ma, B., ... & Li, X. (2026). Invisible Image Watermark Attacks: A Survey.
Su, J., Cai, C., Zhu, F., He, C., Xu, X., Guan, D., & Si, C. (2024, September). Momentum auxiliary network for supervised local learning. In European Conference on Computer Vision (pp. 276-292). Cham: Springer Nature Switzerland.
Yu, C., Li, P., Wu, H., Wen, Y., Deng, B., & Xiong, H. (2024). USM: Unbiased Survey Modeling for Limiting Negative User Experiences in Recommendation Systems. arXiv preprint arXiv:2412.10674.
Wu, X., Gao, D., Yao, J., Qian, Q., & Song, J. (2025). Optimization of Single-Track Train Schedules with Cyclic Operation Strategies. In H. Fujita, A. Hernandez-Matamoros, & Y. Watanobe (Eds.), Proceedings of the 24th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques (SoMeT_25) (pp. 197-206). (Frontiers in Artificial Intelligence and Applications; Vol. 411). IOS Press BV. https://doi.org/10.3233/FAIA250522
Liu, T., He, J., Zhou, R., Song, J., Liu, H., & Liang, Y. (2025). Revolutionizing clinical decision making through deep learning and topic modeling for pathway optimization. Scientific Reports, 15(1), Article 28787. https://doi.org/10.1038/s41598-025-12679-z
Ma, C., Song, J., Xu, Y., Fan, H., Wu, X., & Sun, T. (2024). Vehicle-Based Machine Vision Approaches in Intelligent Connected System. IEEE Transactions on Intelligent Transportation Systems, 25(3), 2827-2836. https://doi.org/10.1109/TITS.2023.3276325
Hao, L., Zhang, S., & Schulzrinne, H. (2025, October). Advancing IoT System Dependability: A Deep Dive into Management and Operation Plane Separation. In 2025 IEEE 11th World Forum on Internet of Things (WF-IoT) (pp. 1-6). IEEE.
Chanda, V., Hao, L., & Schulzrinne, H. (2024, January). From frustration to function: A study on usability challenges in smart home IoT devices. In 2024 IEEE 21st Consumer Communications & Networking Conference (CCNC) (pp. 1-6). IEEE.
Zuo, H., Wu, J., Lim, K. H., Liao, Y., Song, L., Zhu, Y., ... & Zhang, C. (2025). A time series long-short term codec for compression and representation. Applied Intelligence, 55(17), 1-13.
Chen, B., Zuo, H., Liao, Y., & Li, Z. (2024, December). A Data-Driven Analysis of Mental Health Status and Early Warning System for Vocational College Students. In 2024 5th International Conference on Information Science and Education (ICISE-IE) (pp. 312-315). IEEE.
Ning, E., Gao, W., Liu, Y., Yuan, J., Zhang, H., He, S., & Ning, X. (2026). Causally invariant video anomaly detection via counterfactual reasoning and prototype intervention. Pattern Recognition, 113809.