Multimodal Deepfake Detection

Latest papers

35 papers9 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision
Feb 23, 2026Kartik Kuckreja, Parul Gupta, Muhammad Haris Khan +1Deepfake Detection Explainable Deepfake Detection
MBZUAI · Monash University *
MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark
May 16, 2025Florinel-Alin Croitoru, Vlad Hondru, Marius Popescu +3Deepfake Detection Multimodal Deepfake Detection
University of Bucharest · MBZ University of Artificial Intelligence · Linköping University +1
Can Multi-modal (reasoning) LLMs work as deepfake detectors?
Mar 25, 2025Simiao Ren, Yao Yao, Kidus Zewde +8Multimodal Deepfake Detection MLLM Evaluation
Dennis · University of Wisconsin Madison · Columnbia University +1
FORGE: Forensic Reasoning with Grounded Evidence
Mar 20, 2025Rohit Kundu, Shan Jia, Vishal Mohanty +2VLM Adaptation Explainable Deepfake Detection
University of California, Riverside · Google LLC
Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
Nov 29, 2024Florinel-Alin Croitoru, Andrei-Iulian Hiji, Vlad Hondru +7Audio Deepfake Detection Deepfake Detection
Department of Computer Science, University of Bucharest, Romania · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE · Department of Computer Science, University of Central Florida, Orlando, US

Feb 23, 2026J/K move · Enter open · S save

Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision

Kartik Kuckreja, Parul Gupta, Muhammad Haris Khan, Abhinav Dhall

MBZUAI · Monash University *

Deepfake Detection Explainable Deepfake Detection Multimodal Deepfake Detection Multimodal Deception Detection Faithfulness of Language Model Explanations Vision-Language Model-as-a-Judge+1

Open paper AskPDF arXiv

Deepfake detection models often generate natural-language explanations, yet their reasoning is frequently ungrounded in visual evidence, limiting reliability. Existing evaluations measure classification accuracy but overlook reasoning fidelity. We propose DeepfakeJudge, a framework for scalable reasoning supervision and evaluation, that integrates an out-of-distribution benchmark containing recent generative and editing forgeries, a human-annotated subset with visual reasoning labels, and a suite of evaluation models, that specialize in evaluating reasoning rationales without the need for explicit ground truth reasoning rationales. The Judge is optimized through a bootstrapped generator-evaluator process that scales human feedback into structured reasoning supervision and supports both pointwise and pairwise evaluation. On the proposed meta-evaluation benchmark, our reasoning-bootstrapped model achieves an accuracy of 96.2%, outperforming 30x larger baselines. The reasoning judge attains very high correlation with human ratings and 98.9% percent pairwise agreement on the human-annotated meta-evaluation subset. These results establish reasoning fidelity as a quantifiable dimension of deepfake detection and demonstrate scalable supervision for interpretable deepfake reasoning. Our user study shows that participants preferred the reasonings generated by our framework 70% of the time, in terms of faithfulness, groundedness, and usefulness, compared to those produced by other models and datasets. All of our datasets, models, and codebase are open-sourced.

Latest papers

Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision

MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark

Can Multi-modal (reasoning) LLMs work as deepfake detectors?

FORGE: Forensic Reasoning with Grounded Evidence

Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook