Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection

• URL: http://arxiv.org/abs/2608.06865v1
• Date: Fri, 07 Aug 2026 06:44:14 GMT
• Title: Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection
• Abstract summary: malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns.<n>We introduce FaceVid-Forensics-100K, a large-scale deepfake video dataset comprising 100,000 videos and spanning 33 synthesis methods.<n>The dataset provides fine-grained textual annotations of visual observations and verdict-consistent forensic explanations.
• Score: 41.21347360060927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety. However, existing deepfake video benchmarks provide limited coverage of recent synthesis methods and generally lack reliable fine-grained textual annotations. Meanwhile, conventional detectors and multimodal large language models (MLLMs), whether operating as a single model or relying on a single analytical perspective, often fail to capture subtle forgery artifacts, limiting their generalization to emerging AI-generated methods. To address these limitations, we introduce FaceVid-Forensics-100K, a large-scale deepfake video dataset comprising 100,000 videos and spanning 33 synthesis methods across face swapping, face reenactment, and entire-face synthesis, including recent generators such as Seedance 2.0. The dataset provides fine-grained textual annotations of visual observations and verdict-consistent forensic explanations, automatically synthesized through a multi-model aggregation and conflict-resolution pipeline powered by advanced MLLMs. Building on this benchmark, we propose a multi-agent forensic reasoning framework that employs four specialized domain-expert agents to independently analyze forgery cues from four perspectives: texture, lighting, motion, and physics. A judge agent then reconciles their reports to produce a final prediction together with an explanation. Extensive evaluations on out-of-domain test sets show that, despite being composed entirely of small open-source MLLMs, our framework outperforms all methods including closed-source GPT and Gemini models and ranks first across all reported metrics on this benchmark. The project page is available at https://xavierjiezou.github.io/ARGUS/.

Related papers

• HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales [7.669728085259526]
  HumanForge is a unified, large-scale, and multiparadigm human-centric video dataset.<n>Gen2Anno coordinates six specialized agents-ranging from source profiling to MoE-based reference analysis and closed-loop forensic verification-to generate over 18K high-fidelity video segments.
  arXiv  Detail & Related papers  (2026-07-09T17:12:41Z)
• GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver [107.6554560318856]
  GenEraser is a novel framework for generalized and high-fidelity video object and effect removal.<n>We introduce a Multi-Conditional Mixture-of-Experts (MC-MoE) paired with Bipartite Text guidance to fully exploit the multimodal priors of Diffusion Transformers.<n>We also propose a Learnable Deep C'FG' Fusion mechanism to adaptively balance the relative dominance of mask and textual conditions.
  arXiv  Detail & Related papers  (2026-05-28T14:58:36Z)
• RISE-Video: Can Video Generators Decode Implicit World Rules? [71.92434352963427]
  We present RISE-Video, a pioneering reasoning-oriented benchmark for Text-Image-to-Video (TI2V) synthesis.<n>RISE-Video comprises 467 meticulously human-annotated samples spanning eight rigorous categories.<n>We propose an automated pipeline leveraging Large Multimodal Models (LMMs) to emulate human-centric assessment.
  arXiv  Detail & Related papers  (2026-02-05T18:36:10Z)
• SynthForensics: A Multi-Generator Benchmark for Detecting Synthetic Video Deepfakes [5.341795386333291]
  We introduce SynthForensics, to the best of our knowledge the first human-centric benchmark for detecting purely synthetic video deepfakes.<n>The benchmark comprises 6,815 unique videos from five architecturally distinct, state-of-the-art open-source T2V models.<n>We observe a mean performance drop of $29.19%$ AUC, with some methods performing worse than random chance, and top models losing over 30 points under heavy compression.
  arXiv  Detail & Related papers  (2026-02-04T16:47:37Z)
• Your One-Stop Solution for AI-Generated Video Detection [26.581301251283943]
  generative modeling can create remarkably realistic synthetic videos.<n>However, two key limitations hinder the development of this field.<n>We propose AIGVDBench, a benchmark designed to be comprehensive and representative.
  arXiv  Detail & Related papers  (2026-01-16T07:02:06Z)
• EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning [58.42596067220998]
  deepfake video technology has not only facilitated artistic creation but also made it easier to spread misinformation.<n>Traditional deepfake video detection methods face issues such as a lack of transparency in their principles and insufficient capabilities to cope with forgery techniques.<n>This paper proposes the explainable deepfake video detection (EDVD) task and designs the EDVD-LLaMA multimodal reasoning framework.
  arXiv  Detail & Related papers  (2025-10-18T10:34:05Z)
• Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images [96.43608872116347]
  AnomReason is a large-scale benchmark with structured annotations as quadruple textbfAnomAgent<n>AnomReason and AnomAgent serve as a foundation for measuring and improving the semantic plausibility of AI-generated images.
  arXiv  Detail & Related papers  (2025-10-11T14:09:24Z)
• Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation [31.737159092430108]
  We study different generative architectures, searching and identifying discriminative features that are unbiased, robust to impairments, and shared across models.<n>We introduce a novel data augmentation strategy based on the wavelet decomposition and replace specific frequency-related bands to drive the model to exploit more relevant forensic cues.<n>Our method achieves a significant accuracy improvement over state-of-the-art detectors and obtains excellent results even on very recent generative models.
  arXiv  Detail & Related papers  (2025-06-20T07:36:59Z)
• DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning [58.70446237944036]
  DAVID-X is the first dataset to pair AI-generated videos with detailed defect-level, temporal-spatial annotations and written rationales.<n>We present DAVID-XR1, a video-language model designed to deliver an interpretable chain of visual reasoning.<n>Our results highlight the promise of explainable detection methods for trustworthy identification of AI-generated video content.
  arXiv  Detail & Related papers  (2025-06-13T13:39:53Z)
• AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detection [20.800161778433914]
  Human-centric video generation methods can synthesize entire human bodies with controllable movements.<n>Existing detection methods largely overlook the growing risks posed by such full-body synthetic content.<n>We propose AvatarShield, a novel multimodal human-centric synthetic video detection framework.
  arXiv  Detail & Related papers  (2025-05-21T06:43:34Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.