A dual-encoder deepfake detector pairs a frozen specialist with a LoRA-tuned MLLM, trained first via binary alignment then via RL to reward explain-then-classify behavior, yielding improved cross-dataset performance and interpretability.
So-fake: Benchmarking and explain- ing social media image forgery detection
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
dataset 2
citation-polarity summary
roles
dataset 2polarities
use dataset 2representative citing papers
ReAlign distills LLM-generated reasoning texts into a lightweight AIGI forgery detector via contrastive image-text alignment to improve generalization on complex forgeries.
JECA^2 is a new white-box attack method using Grad-CAM-guided perturbations and prompt embedding optimization to achieve judgment-explanation consistent adversarial attacks on forensic VLMs.
Face-Trace attributes synthetic face images to known generators, rejects images from unseen generators via an energy score, and clusters the rejected images into groups corresponding to distinct unknown generators, including in an incremental setting.
Omni-Fake delivers a unified multimodal deepfake benchmark dataset and RL-driven detector that reports gains in accuracy, cross-modal generalization, and explainability over prior baselines.
ForenAgent, an MLLM that writes and runs Python forensics tools over multiple turns, beats prior image-forgery detectors on its new FABench benchmark and on SIDA-Test.
FakeVLM-R1 combines GRPO reinforcement learning with critical-thinking CoT and a physics-annotated FakeClue++ dataset to reach claimed SOTA synthetic image detection while reducing over-rejection of real images.
LoRA-based pairwise training with distortion and size simulations boosts robust AIGI detection under severe distortions, placing third in the NTIRE challenge.
The NTIRE 2026 challenge provides a dataset of over 294,000 real and AI-generated images with 36 transformations to benchmark robust detection models.
HEDGE is a heterogeneous ensemble using progressive DINOv3 training, multi-scale features, and MetaCLIP2 diversity with dual-gating fusion to achieve robust AI-generated image detection and 4th place in the NTIRE 2026 challenge.
citing papers explorer
-
The Regularizing Power of Language-Training Deepfake Detectors
A dual-encoder deepfake detector pairs a frozen specialist with a LoRA-tuned MLLM, trained first via binary alignment then via RL to reward explain-then-classify behavior, yielding improved cross-dataset performance and interpretability.
-
ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation
ReAlign distills LLM-generated reasoning texts into a lightweight AIGI forgery detector via contrastive image-text alignment to improve generalization on complex forgeries.
-
JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models
JECA^2 is a new white-box attack method using Grad-CAM-guided perturbations and prompt embedding optimization to achieve judgment-explanation consistent adversarial attacks on forensic VLMs.
-
Face-Trace: Open-Set Attribution and Progressive Discovery of Synthetic Face Generators
Face-Trace attributes synthetic face images to known generators, rejects images from unseen generators via an energy score, and clusters the rejected images into groups corresponding to distinct unknown generators, including in an incremental setting.
-
Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection
Omni-Fake delivers a unified multimodal deepfake benchmark dataset and RL-driven detector that reports gains in accuracy, cross-modal generalization, and explainability over prior baselines.
-
Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection
ForenAgent, an MLLM that writes and runs Python forensics tools over multiple turns, beats prior image-forgery detectors on its new FABench benchmark and on SIDA-Test.
-
FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection
FakeVLM-R1 combines GRPO reinforcement learning with critical-thinking CoT and a physics-annotated FakeClue++ dataset to reach claimed SOTA synthetic image detection while reducing over-rejection of real images.
-
Boosting Robust AIGI Detection with LoRA-based Pairwise Training
LoRA-based pairwise training with distortion and size simulations boosts robust AIGI detection under severe distortions, placing third in the NTIRE challenge.
-
NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild
The NTIRE 2026 challenge provides a dataset of over 294,000 real and AI-generated images with 36 transformations to benchmark robust detection models.
-
HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild
HEDGE is a heterogeneous ensemble using progressive DINOv3 training, multi-scale features, and MetaCLIP2 diversity with dual-gating fusion to achieve robust AI-generated image detection and 4th place in the NTIRE 2026 challenge.