FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
Cnn- generated images are surprisingly easy to spot... for now
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
fields
cs.CV 6verdicts
UNVERDICTED 6representative citing papers
MAFL uses adversarial training to suppress pattern and content biases, guiding models to learn shared generative features for better cross-model generalization in detecting AI images.
LAA-X uses multi-task learning with explicit localized artifact attention and blending synthesis to build a deepfake detector that generalizes to high-quality and unseen manipulations after training only on real and pseudo-fake samples.
FADNet reformulates face forgery detection as one-class learning on real faces only, using EDL uncertainty and a PFIG to achieve 96.63% average accuracy and 98.83% precision on DF40 and ASFD benchmarks.
EMSFD uses Dirichlet-based evidence modeling to capture prediction uncertainty in synthetic face detection and applies uncertainty-driven active learning to achieve 15% higher accuracy than prior methods.
The proposed steganography-based attribution system with CLIP multimodal fusion achieves robust watermarking under distortions and 0.99 AUC-ROC for harm detection, enabling traceable AI content accountability.
citing papers explorer
-
Toward Generalizable Forgery Detection and Reasoning
FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
-
Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection
MAFL uses adversarial training to suppress pattern and content biases, guiding models to learn shared generative features for better cross-model generalization in detecting AI images.
-
LAA-X: Unified Localized Artifact Attention for Quality-Agnostic and Generalizable Face Forgery Detection
LAA-X uses multi-task learning with explicit localized artifact attention and blending synthesis to build a deepfake detector that generalizes to high-quality and unseen manipulations after training only on real and pseudo-fake samples.
-
Only Train Once: Uncertainty-Aware One-Class Learning for Face Authenticity Detection
FADNet reformulates face forgery detection as one-class learning on real faces only, using EDL uncertainty and a PFIG to achieve 96.63% average accuracy and 98.83% precision on DF40 and ASFD benchmarks.
-
Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning
EMSFD uses Dirichlet-based evidence modeling to capture prediction uncertainty in synthetic face detection and applies uncertainty-driven active learning to achieve 15% higher accuracy than prior methods.
-
Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection
The proposed steganography-based attribution system with CLIP multimodal fusion achieves robust watermarking under distortions and 0.99 AUC-ROC for harm detection, enabling traceable AI content accountability.