Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection
Summary
This paper introduces FaceVid-Forensics-100K, a large-scale deepfake video dataset with fine-grained annotations, and proposes a multi-agent forensic reasoning framework (ARGUS) that uses four specialized expert agents and a judge agent to outperform closed-source models on deepfake detection.
View Cached Full Text
Cached at: 08/10/26, 06:16 PM
Paper page - Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection
Source: https://huggingface.co/papers/2608.06865
Abstract
ThemalicioususeofgenerativeartificialintelligencetocreatehighlyrealisticdeepfakevideosraisesseriousethicalconcernsandposessubstantialchallengestoAIsafety.However,existingdeepfakevideobenchmarksprovidelimitedcoverageofrecentsynthesismethodsandgenerallylackreliablefine-grainedtextualannotations.Meanwhile,conventionaldetectorsandmultimodallargelanguagemodels(MLLMs),whetheroperatingasasinglemodelorrelyingonasingleanalyticalperspective,oftenfailtocapturesubtleforgeryartifacts,limitingtheirgeneralizationtoemergingAI-generatedmethods.Toaddresstheselimitations,weintroduceFaceVid-Forensics-100K,alarge-scaledeepfakevideodatasetcomprising100,000videosandspanning33synthesismethodsacrossfaceswapping,facereenactment,andentire-facesynthesis,includingrecentgeneratorssuchasSeedance2.0.Thedatasetprovidesfine-grainedtextualannotationsofvisualobservationsandverdict-consistentforensicexplanations,automaticallysynthesizedthroughamulti-modelaggregationandconflict-resolutionpipelinepoweredbyadvancedMLLMs.Buildingonthisbenchmark,weproposeamulti-agentforensicreasoningframeworkthatemploysfourspecializeddomain-expertagentstoindependentlyanalyzeforgerycuesfromfourperspectives:texture,lighting,motion,andphysics.Ajudgeagentthenreconcilestheirreportstoproduceafinalpredictiontogetherwithanexplanation.Extensiveevaluationsonout-of-domaintestsetsshowthat,despitebeingcomposedentirelyofsmallopen-sourceMLLMs,ourframeworkoutperformsallmethodsincludingclosed-sourceGPTandGeminimodelsandranksfirstacrossallreportedmetricsonthisbenchmark.Theprojectpageisavailableathttps://xavierjiezou.github.io/ARGUS/.
View arXiv pageView PDFProject pageGitHub0Add to collection
Get this paper in your agent:
hf papers read 2608\.06865
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.06865 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.06865 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.06865 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection
WeVisForensics introduces a self-evolving multi-agent framework with dual-timescale policy optimization (DTPO) for detecting AI-generated videos, achieving 95.2% average detection accuracy—9.0% above the prior best detector—with localized forensic evidence, plus a curated ForenCue-30K dataset.
Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning
This paper presents a unified global-to-local paradigm for video anomaly detection, introducing a training-free framework (GtS) and a tool-augmented agentic reasoning method with reinforcement learning, along with a new benchmark VAGU-T and metric JeAUG.
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
Video-DeepResearch (Video-DR) extends multimodal agents from static images to continuous video streams, introducing a decoupled perception-exploration pipeline and a new benchmark Video-DR-Bench. Their Video-DeepResearch-35B-A3B model achieves 64.0% accuracy, surpassing Claude-4.5-Sonnet, GPT-5, and Gemini 2.5 Pro.
Detecting deepfakes, in a world where even reality is suspect
A look at the growing challenge of detecting AI-generated deepfakes as synthetic media becomes indistinguishable from reality, and the emerging tools and strategies to verify authentic content.
Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling
This paper proposes UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem using multi-agent collaborative reasoning and tool-augmented evidence retrieval. It outperforms baselines on global urban datasets for carbon emissions, GDP, and population estimation, achieving an average 8.1% improvement in R².