Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kuckreja, Kartik, Gupta, Parul, Khan, Muhammad Haris, Dhall, Abhinav
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Tell me Habibi, is it Real or Fake?
por: Kuckreja, Kartik, et al.
Publicado: (2025)

AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations
por: Cai, Zhixi, et al.
Publicado: (2025)

LayLens: Improving Deepfake Understanding through Simplified Explanations
por: Narang, Abhijeet, et al.
Publicado: (2025)

Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual Manipulations
por: Gupta, Parul, et al.
Publicado: (2025)

Improving Personalized Image Generation through Social Context Feedback
por: Gupta, Parul, et al.
Publicado: (2025)

Conditional Distribution Modelling for Few-Shot Image Synthesis with Diffusion Models
por: Gupta, Parul, et al.
Publicado: (2024)

Generation and Detection of Sign Language Deepfakes - A Linguistic and Visual Analysis
por: Naeem, Shahzeb, et al.
Publicado: (2024)

VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding
por: Waheed, Abdul, et al.
Publicado: (2025)

VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping
por: Baliah, Sanoojan, et al.
Publicado: (2026)

1M-Deepfakes Detection Challenge
por: Cai, Zhixi, et al.
Publicado: (2024)

Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detection
por: Chuchra, Akanksha, et al.
Publicado: (2026)

DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition
por: Gupta, Parul, et al.
Publicado: (2024)

SFANet: Spatial-Frequency Attention Network for Deepfake Detection
por: Ahire, Vrushank, et al.
Publicado: (2025)

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs
por: Janjua, Muhammad Kamran, et al.
Publicado: (2026)

Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Counting
por: Zhang, Xiaowen, et al.
Publicado: (2026)

AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
por: Cai, Zhixi, et al.
Publicado: (2023)

Robust and Label-Efficient Deep Waste Detection
por: Abid, Hassan, et al.
Publicado: (2025)

Improving Pseudo-labelling and Enhancing Robustness for Semi-Supervised Domain Generalization
por: Khan, Adnan, et al.
Publicado: (2024)

Don't Judge by the Look: Towards Motion Coherent Video Representation
por: Zhang, Yitian, et al.
Publicado: (2024)

GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
por: Danish, Muhammad Sohail, et al.
Publicado: (2024)

Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks
por: Zalcher, Amit, et al.
Publicado: (2025)

A Multi-Modal Neuro-Symbolic Approach for Spatial Reasoning-Based Visual Grounding in Robotics
por: Jahangard, Simindokht, et al.
Publicado: (2025)

Audios Don't Lie: Multi-Frequency Channel Attention Mechanism for Audio Deepfake Detection
por: Feng, Yangguang
Publicado: (2024)

Judging from Support-set: A New Way to Utilize Few-Shot Segmentation for Segmentation Refinement Process
por: Moon, Seonghyeon, et al.
Publicado: (2024)

VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection
por: Han, Hui, et al.
Publicado: (2026)

MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding
por: Madan, Surbhi, et al.
Publicado: (2024)

Show, Don't Tell: Morphing Latent Reasoning into Image Generation
por: Chen, Harold Haodong, et al.
Publicado: (2026)

Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy
por: Ni, Minheng, et al.
Publicado: (2024)

Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins
por: Ray, Rahul D
Publicado: (2026)

Modality-Fair Preference Optimization for Trustworthy MLLM Alignment
por: Jiang, Songtao, et al.
Publicado: (2024)

Judge Anything: MLLM as a Judge Across Any Modality
por: Pu, Shu, et al.
Publicado: (2025)

Realism to Deception: Investigating Deepfake Detectors Against Face Enhancement
por: Saeed, Muhammad Saad, et al.
Publicado: (2025)

CountZES: Counting via Zero-Shot Exemplar Selection
por: Siddiqui, Muhammad Ibraheem, et al.
Publicado: (2025)

How Effective are Self-Supervised Models for Contact Identification in Videos
por: Gunawardhana, Malitha, et al.
Publicado: (2024)

Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift
por: Khan, Mohammed Abdul Hafeez, et al.
Publicado: (2025)

XAI-Based Detection of Adversarial Attacks on Deepfake Detectors
por: Pinhasov, Ben, et al.
Publicado: (2024)

Real, fake and synthetic faces -- does the coin have three sides?
por: Naeem, Shahzeb, et al.
Publicado: (2024)

The Future of Reading: Don't Worry. It Might Be Better than You Think
por: Green, John
Publicado: (2010)

Zero-shot HOI Detection with MLLM-based Detector-agnostic Interaction Recognition
por: Xuan, Shiyu, et al.
Publicado: (2026)

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning
por: Li, Ming, et al.
Publicado: (2025)