This work introduces ManiVid, a unified forensic analysis task covering forgery detection, artifact grounding, and anomaly explanation for manipulated videos, and proposes ManiVidLens, a unified framework for explainable video forgery analysis.
Abstract
Rapid advances in AI-generated video (AIGV) have increased the risks posed by deceptive video manipulation. Unlike fully synthetic videos, manipulated videos retain most source content and alter only localized regions, making forensic analysis particularly challenging. Existing video forgery research faces two limitations in both data and methodology: (1) High-quality datasets and benchmarks tailored for manipulated videos remain scarce. (2) Multimodal large language models (MLLMs) extend forgery analysis beyond binary classification but struggle to use low-level forensic cues and provide precise pixel-level grounding. Specifically, we introduce ManiVid, a unified forensic analysis task covering forgery detection, artifact grounding, and anomaly explanation for manipulated videos. We construct ManiVid-38K, the first dataset to combine paired, open-vocabulary localized manipulations of general videos with authenticity labels, forgery masks, and anomaly explanations. It comprises about 19K manually verified real-fake video pairs, mostly at 1080P resolution, generated under 2 paradigms with 15 powerful generation models. We sample 1K pairs for ManiVidBench, balanced across six manipulation types and generation models for fair evaluation. We further propose ManiVidLens, a unified framework for explainable video forgery analysis. Its Forensic Evidence Router supplies shared low-level forensic evidence for multimodal reasoning and video segmentation. Its Prompt Distill Module converts grounding states into semantic and geometric prompts and distills spatial priors for mask decoding and full-video propagation. ManiVidLens achieves relative gains over the strongest comparison methods in artifact grounding (+21.1% mIoU; +21.3% J&F) and anomaly explanation (+131.3% ROUGE-L; +9.9% CSS). Its forgery detection remains comparable to dedicated classifiers (0.914 Acc; 0.913 F1).
XAI-VFF is presented, a unified Explainable AI framework that combines Gradient-weighted Class Activation Mapping (Grad-CAM), SHapley Additive exPlanations (SHAP), and Local Interpretable Model-Agnostic Explanations (LIME) for video forgery explanations.
S. P, R. Priya· International journal of com...· 0 citations
This work introduces meta-detection into AI-generated video detection, enabling reliable forgery detection by jointly optimizing predicted labels and supporting evidence within reinforcement learning, and introduces evidence-aware credit assignment, which preserves reliable label supervision while encouraging detectors...
Bo-Wei Liu, Zheng Lu, Yuhan Bian et al.· 1 citation
Deepfake detection in videos remains challenging, as manipulated content may appear visually consistent at the frame level while exhibiting subtle temporal inconsistencies. This paper introduces an interpretable deepfake detection framework that models spatially and temporally coherent facial features in video sequence...
Chahira Benhama, M. Allili, Assia Hamadene· 0 citations
A decomposed chain-of-thought (CoT) pipeline that combines a document tampering detector (DTD) with two Qwen3-VL-32B vision-language models, each LoRA-adapted to a distinct sub-task is presented.
Kirill Koltsov, A. Gushchin, D. Vatolin et al.· Proceedings of the 34th ACM...· 0 citations
This research provides a resilient forensic layer for digital identity verification, ensuring evidence integrity in the GenAI era by proposing a novel Multimodal Deep Learning framework designed to detect high-fidelity Deepfakes by exploiting audio visual temporal inconsistencies.
H. Truong, D. T. Luong, Tuan Tran· Journal of Science and Techn...· 0 citations
This paper proposes TempJail, a novel temporal jailbreak framework for I2V systems, and investigates three attack scenarios and uncover a temporal vulnerability in I2V systems: unsafe semantics may emerge not from a single frame, but from semantic composition over time.
Qiang Lu, Zehui Guo, D. Gan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.