SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model.

Zhenglin Huang Zhenglin Huang Jinwei Hu Xiangtai Li Yiwei He Xingyu Zhao 0001 Bei Peng 0001 Baoyuan Wu Xiaowei Huang 0001 Guangliang Cheng SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model. 28831-28841 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Huang_SIDA_Social_Media_Image_Deepfake_Detection_Localization_and_Explanation_with_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.02685 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#HuangHLH00W0C25 Tianxiao Li Zhenglin Huang Haiquan Wen Yiwei He Shuchang Lyu Baoyuan Wu Guangliang Cheng RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection. 11746-11755 2025 ACM Multimedia https://doi.org/10.1145/3746027.3754798 conf/mm/2025 db/conf/mm/mm2025.html#LiHWHLWC25

Jinwei Hu Zhenglin Huang Xiangyu Yin 0001 Wenjie Ruan Guangliang Cheng Yi Dong 0002 Xiaowei Huang 0001 FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model. 2025 February abs/2502.01472 CoRR https://doi.org/10.48550/arXiv.2502.01472 db/journals/corr/corr2502.html#abs-2502-01472 streams/journals/corr

Haiquan Wen Yiwei He Zhenglin Huang Tianxiao Li Zihan Yu Xingru Huang Lu Qi 0001 Baoyuan Wu Xiangtai Li Guangliang Cheng BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation. 2025 May abs/2505.12620 CoRR https://doi.org/10.48550/arXiv.2505.12620 db/journals/corr/corr2505.html#abs-2505-12620 streams/journals/corr

Zhenglin Huang Tianxiao Li Xiangtai Li Haiquan Wen Yiwei He Jiangning Zhang Hao Fei 0001 Xi Yang 0008 Xiaowei Huang 0001 Bei Peng 0001 Guangliang Cheng So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection. 2025 May abs/2505.18660 CoRR https://doi.org/10.48550/arXiv.2505.18660 db/journals/corr/corr2505.html#abs-2505-18660 streams/journals/corr

Zhenglin Huang Qifa Yan Bin Dai 0003 Xiaohu Tang 0004 A Simple but Accurate Approximation for Multivariate Gaussian Rate-Distortion Function and Its Application in Maximal Coding Rate Reduction. 2025 June abs/2506.18613 CoRR https://doi.org/10.48550/arXiv.2506.18613 db/journals/corr/corr2506.html#abs-2506-18613 streams/journals/corr

Yiwei He Xiangtai Li Zhenglin Huang Yi Dong Hao Fei 0001 Jiangning Zhang Baoyuan Wu Guangliang Cheng Towards Explainable Bilingual Multimodal Misinformation Detection and Localization. 2025 June abs/2506.22930 CoRR https://doi.org/10.48550/arXiv.2506.22930 db/journals/corr/corr2506.html#abs-2506-22930 streams/journals/corr

Haiquan Wen Tianxiao Li Zhenglin Huang Yiwei He Guangliang Cheng BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM. 2025 July abs/2507.14632 CoRR https://doi.org/10.48550/arXiv.2507.14632 db/journals/corr/corr2507.html#abs-2507-14632 streams/journals/corr

Tianxiao Li Zhenglin Huang Haiquan Wen Yiwei He Shuchang Lyu Baoyuan Wu Guangliang Cheng RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection. 2025 August abs/2508.04524 CoRR https://doi.org/10.48550/arXiv.2508.04524 db/journals/corr/corr2508.html#abs-2508-04524 streams/journals/corr

Xinmiao Huang Qisong He Zhenglin Huang Boxuan Wang Zhuoyun Li Guangliang Cheng Yi Dong 0002 Xiaowei Huang 0001 Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models. 2025 October abs/2510.13394 CoRR https://doi.org/10.48550/arXiv.2510.13394 db/journals/corr/corr2510.html#abs-2510-13394 streams/journals/corr

Zhenglin Huang Jason Li Haiquan Wen Tianxiao Li Xi Yang 0008 Lu Qi 0001 Bei Peng 0001 Xiaowei Huang 0001 Ming-Hsuan Yang 0001 Guangliang Cheng Rethinking Cross-Generator Image Forgery Detection through DINOv3. 2025 November abs/2511.22471 CoRR https://doi.org/10.48550/arXiv.2511.22471 db/journals/corr/corr2511.html#abs-2511-22471 streams/journals/corr

Zhenglin Huang Jinwei Hu Xiangtai Li Yiwei He Xingyu Zhao 0001 Bei Peng 0001 Baoyuan Wu Xiaowei Huang 0001 Guangliang Cheng SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model. 2024 abs/2412.04292 CoRR https://doi.org/10.48550/arXiv.2412.04292 db/journals/corr/corr2412.html#abs-2412-04292 streams/journals/corr

Zhenglin Huang Xiaoan Bao Na Zhang Qingqi Zhang Xiao Tu Biao Wu Xi Yang IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers. 2023 NeurIPS http://papers.nips.cc/paper_files/paper/2023/hash/c917d8b9e01427f3184d80ade22f4d1f-Abstract-Conference.html conf/nips/2023 db/conf/nips/neurips2023.html#HuangBZZTWY23

Zhenglin Huang Xianan Bao Na Zhang Qingqi Zhang Xiaomei Tu Biao Wu Xi Yang IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers. 2023 abs/2310.04780 CoRR https://doi.org/10.48550/arXiv.2310.04780 db/journals/corr/corr2310.html#abs-2310-04780

Xianan Bao Xiaoan Bao Guangliang Cheng Bin Dai 0003 Yi Dong Yi Dong 0002 Hao Fei 0001 Qisong He Yiwei He Jinwei Hu Xiaowei Huang 0001 Xingru Huang Xinmiao Huang Jason Li Tianxiao Li Xiangtai Li Zhuoyun Li Shuchang Lyu Bei Peng 0001 Lu Qi 0001 Wenjie Ruan Xiaohu Tang 0004 Xiao Tu Xiaomei Tu Boxuan Wang Haiquan Wen Baoyuan Wu Biao Wu Qifa Yan Ming-Hsuan Yang 0001 Xi Yang Xi Yang 0008 Xiangyu Yin 0001 Zihan Yu Jiangning Zhang Na Zhang Qingqi Zhang Xingyu Zhao 0001