UniGADD: Universal Generator-Agnostic Deepfake Detector
cs.CV, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/Aghasanli/UniGADD-Universal-Generator-Agnostic-Deepfake-Detector
Terminology
Sources
- CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Raising the Bar of AI-generated Image Detection with CLIP
- Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model
- Supervised Contrastive Learning
- SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes
- DINOv2: Learning Robust Visual Features without Supervision
- Learning Transferable Visual Models From Natural Language Supervision
- Towards Total Recall in Industrial Anomaly Detection
- FaceForensics++: Learning to Detect Manipulated Facial Images
- Real Face Foundation Representation Learning for Generalized Deepfake Detection
- Contrastive Pseudo Learning for Open-World DeepFake Attribution
- Clustering Properties of Self-Supervised Learning
- ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs