# Fact or Fake? Assessing the Role of Deepfake Detectors in Multimodal Misinformation Detection

arXiv: https://arxiv.org/abs/2602.01854 · HTML: https://mlsanity.com/paper/2602.01854/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 56 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [Global Texture Enhancement for Fake Face Detection in the Wild](https://mlsanity.com/paper/2002.00133/) (2020)
- [Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection](https://mlsanity.com/paper/2312.16649/) (2023)
- [SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model](https://mlsanity.com/paper/2412.04292/) (2024)
- [SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2403.03170/) (2024)
- [Multimodal Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2305.13507/) (2023)
- [Can We Leave Deepfake Data Behind in Training Deepfake Detector?](https://mlsanity.com/paper/2408.17052/) (2024)
- [DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts](https://mlsanity.com/paper/2412.10510/) (2024)
- [COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learning](https://mlsanity.com/paper/2101.06278/) (2021)
- [Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks](https://mlsanity.com/paper/2406.04932/) (2024)
- [Multimodal Misinformation Detection using Large Vision-Language Models](https://mlsanity.com/paper/2407.14321/) (2024)
- [Deepfake Detection that Generalizes Across Benchmarks](https://mlsanity.com/paper/2508.06248/) (2025)
- [RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection](https://mlsanity.com/paper/2311.09939/) (2023)
- [Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?](https://mlsanity.com/paper/2410.04616/) (2024)
- [Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook](https://mlsanity.com/paper/2411.19537/) (2024)
- [TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection](https://mlsanity.com/paper/2509.04448/) (2025)
- [Crafting Synthetic Realities: Examining Visual Realism and Misinformation Potential of Photorealistic AI-Generated Images](https://mlsanity.com/paper/2409.17484/) (2024)
- [VeriTaS: The First Dynamic Benchmark for Multimodal Automated Fact-Checking](https://mlsanity.com/paper/2601.08611/) (2026)
- [RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking](https://mlsanity.com/paper/2507.09174/) (2025)
- [T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search](https://mlsanity.com/paper/2505.19768/) (2025)
- [Deepfake Detection of Face Images based on a Convolutional Neural Network](https://mlsanity.com/paper/2503.11389/) (2025)
- [Image-Text Out-Of-Context Detection Using Synthetic Multimodal Misinformation](https://mlsanity.com/paper/2403.08783/) (2024)
- [LookupForensics: A Large-Scale Multi-Task Dataset for Multi-Phase Image-Based Fact Verification](https://mlsanity.com/paper/2407.18614/) (2024)
- [Fact-Checking with Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis](https://mlsanity.com/paper/2504.10166/) (2025)

## Built on by (most cited first, 1 of 1)

- [Detecting AI-Generated Video: A Vision-Language Dual-View Survey](https://mlsanity.com/paper/2607.10787/) (2026)

## Abstract (arXiv)

In multimodal misinformation, deception usually arises not just from pixel-level manipulations in an image, but from the semantic and contextual claim jointly expressed by the image-text pair. Yet most deepfake detectors, engineered to detect pixel-level forgeries, do not account for claim-level meaning, despite their growing integration in automated fact-checking (AFC) pipelines. This raises a central scientific and practical question: Do pixel-level detectors contribute useful signal for verifying image-text claims, or do they instead introduce misleading authenticity priors that undermine evidence-based reasoning? We provide the first systematic analysis of deepfake detectors in the context of multimodal misinformation detection. Using two complementary benchmarks, MMFakeBench and DGM4, we evaluate: (1) state-of-the-art image-only deepfake detectors, (2) an evidence-driven fact-checking system that performs tool-guided retrieval via Monte Carlo Tree Search (MCTS) and engages in deliberative inference through Multi-Agent Debate (MAD), and (3) a hybrid fact-checking system that injects detector outputs as auxiliary evidence. Results across both benchmark datasets show that deepfake detectors offer limited standalone value, achieving F1 scores in the range of 0.26-0.53 on MMFakeBench and 0.33-0.49 on DGM4, and that incorporating their predictions into fact-checking pipelines consistently reduces performance by 0.04-0.08 F1 due to non-causal authenticity assumptions. In contrast, the evidence-centric fact-checking system achieves the highest performance, reaching F1 scores of approximately 0.81 on MMFakeBench and 0.55 on DGM4. Overall, our findings demonstrate that multimodal claim verification is driven primarily by semantic understanding and external evidence, and that pixel-level artifact signals do not reliably enhance reasoning over real-world image-text misinformation.