# Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning

arXiv: https://arxiv.org/abs/2508.21048 · HTML: https://mlsanity.com/paper/2508.21048/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 57 of its 112 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 57)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2503.12937/) (2025)
- [The Deepfake Detection Challenge (DFDC) Preview Dataset](https://mlsanity.com/paper/1910.08854/) (2019)
- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [A Sanity Check for AI-generated Image Detection](https://mlsanity.com/paper/2406.19435/) (2024)
- [DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection](https://mlsanity.com/paper/2307.01426/) (2023)
- [The DeepFake Detection Challenge (DFDC) Dataset](https://mlsanity.com/paper/2006.07397/) (2020)
- [HART: Efficient Visual Generation with Hybrid Autoregressive Transformer](https://mlsanity.com/paper/2410.10812/) (2024)
- [Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining](https://mlsanity.com/paper/2504.07912/) (2025)
- [MiMo-VL Technical Report](https://mlsanity.com/paper/2506.03569/) (2025)
- [FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models](https://mlsanity.com/paper/2410.02761/) (2024)
- [Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2411.15633/) (2024)
- [Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation](https://mlsanity.com/paper/2508.09987/) (2025)
- [Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation](https://mlsanity.com/paper/2503.14905/) (2025)
- [Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL](https://mlsanity.com/paper/2505.10832/) (2025)
- [FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant](https://mlsanity.com/paper/2408.10072/) (2024)
- [Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning](https://mlsanity.com/paper/2506.04207/) (2025)

## Built on by (most cited first, 23 of 23)

- [Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning](https://mlsanity.com/paper/2512.15693/) (2025)
- [VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning](https://mlsanity.com/paper/2602.08828/) (2026)
- [Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images](https://mlsanity.com/paper/2510.10231/) (2025)
- [Venus-DeFakerOne: Unified Fake Image Detection & Localization](https://mlsanity.com/paper/2605.14091/) (2026)
- [EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection](https://mlsanity.com/paper/2603.17343/) (2026)
- [On the Holistic Approach for Detecting Human Image Forgery](https://mlsanity.com/paper/2601.04715/) (2026)
- [Revisiting Image Manipulation Localization under Realistic Manipulation Scenarios](https://mlsanity.com/paper/2509.20006/) (2025)
- [VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection](https://mlsanity.com/paper/2603.21526/) (2026)
- [Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection](https://mlsanity.com/paper/2607.27113/) (2026)
- [HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild](https://mlsanity.com/paper/2604.03555/) (2026)
- [LOGER: Local--Global Ensemble for Robust Deepfake Detection in the Wild](https://mlsanity.com/paper/2604.03558/) (2026)
- [HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection](https://mlsanity.com/paper/2605.26421/) (2026)
- [Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation](https://mlsanity.com/paper/2608.08009/) (2026)
- [Explainable Deepfake Detection with Feature-robust Augmentation and Evidence-grounded Explanation Optimization](https://mlsanity.com/paper/2608.20913/) (2026)
- [Explainable AI-Generated Image Detection RewardBench](https://mlsanity.com/paper/2511.12363/) (2025)
- [ForensicZip: More Tokens are Better but Not Necessary in Forensic Vision-Language Models](https://mlsanity.com/paper/2603.12208/) (2026)
- [Generalizable Detection of AI Generated Images with Large Models and Fuzzy Decision Tree](https://mlsanity.com/paper/2603.28508/) (2026)
- [TRACE: Trajectory Representation and Consistency Estimation for AI-Generated Video Detection](https://mlsanity.com/paper/2609.25775/) (2026)
- [IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection](https://mlsanity.com/paper/2609.33585/) (2026)
- [DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detection](https://mlsanity.com/paper/2609.35096/) (2026)
- [RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2609.36822/) (2026)
- [Typographic Attack Against VLM-based AI-generated Image Detection](https://mlsanity.com/paper/2609.39662/) (2026)
- [WorldFact-Bench: Beyond Image-Internal Plausibility to Image-World Consistency](https://mlsanity.com/paper/2610.11184/) (2026)

## Abstract (arXiv)

Deepfake detection remains a formidable challenge due to the complex and evolving nature of fake content in real-world scenarios. However, existing academic benchmarks suffer from severe discrepancies from industrial practice, typically featuring homogeneous training sources and low-quality testing images, which hinder the practical deployments of current detectors. To mitigate this gap, we introduce HydraFake, a dataset that simulates real-world challenges with hierarchical generalization testing. Specifically, HydraFake involves diversified deepfake techniques and in-the-wild forgeries, along with rigorous training and evaluation protocol, covering unseen model architectures, emerging forgery techniques and novel data domains. Building on this resource, we propose Veritas, a multi-modal large language model (MLLM) based deepfake detector. Different from vanilla chain-of-thought (CoT), we introduce pattern-aware reasoning that involves critical reasoning patterns such as "planning" and "self-reflection" to emulate human forensic process. We further propose a two-stage training pipeline to seamlessly internalize such deepfake reasoning capacities into current MLLMs. Experiments on HydraFake dataset reveal that although previous detectors show great generalization on cross-model scenarios, they fall short on unseen forgeries and data domains. Our Veritas achieves significant gains across different OOD scenarios, and is capable of delivering transparent and faithful detection outputs.