ForeAgent combines a Perception-Verdict MLLM architecture with hindsight-driven self-refining via sampling-reflection-evolution to reach 82.18% accuracy on Chameleon and 93.3% mean accuracy across 16 generators on AIGCDetect-Benchmark.
hub
Patchcraft: Exploring texture patch for efficient ai-generated image detection
30 Pith papers cite this work. Polarity classification is still indexing.
30
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Introduces the Impostor benchmark dataset for localizing AIGC image manipulations via agent curation and the PANet model that uses phase and semantic consistency for better detection.
FiSeR uses coarse contrastive separation of natural vs synthetic images plus fine contrastive grouping by generator identity to improve cross-domain AUROC by +10.22 over DIRE baseline on multiple test sets.
PROBE improves AIGI detector generalization to unseen generators by using the detector as a critic to steer manifold-level modifications that produce challenging training samples.
ReAlign distills LLM-generated reasoning texts into a lightweight AIGI forgery detector via contrastive image-text alignment to improve generalization on complex forgeries.
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
LEGO uses multiple generator-specific LoRA modules modulated by an MLP and fused with attention to detect synthetic images, achieving better performance than prior methods while using under 10% of the training data.
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.
ForensicConcept extracts and transfers forensic concepts from AIGI detectors via Transformer attribution, concept codebooks, CleanDIFT references, and CKNNA alignment to improve detection on unseen generators.
DetectZoo is a unified toolkit providing reference implementations of 61 detectors, native loaders for 22 benchmark datasets, and a standardized evaluation pipeline for AI-generated content detection across text, audio, and image modalities.
Color transformations expose statistical discrepancies in synthetic images, supporting a classifier with 93.27% average accuracy and robustness to post-processing.
CoDA is a lightweight detector using a Noise-Quantization Probe on color non-uniformity that reports strong cross-domain results on the new FakeForm benchmark and competitive cross-model performance on standard tests.
STAL transfers spectral tail uplift cues via a frequency teacher to train a spatial detector for AI-generated images, discarding frequency modules at inference for strong cross-generator generalization.
SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.
ANL uses diffusion noise prediction and attention to regularize deepfake detectors for better generalization to unseen synthesis methods without added inference cost.
A multi-agent forensic system integrates multiple evidence sources and debate to detect AI-generated images, reporting 97.05% accuracy on a 6,000-image benchmark while outperforming traditional classifiers.
PGC introduces peak-focusing aggregation of local discriminative clues to calibrate global representations for AI-generated image detection, reporting accuracy gains on a new 15-model commercial benchmark and standard datasets.
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
MDMF detects AI-generated images by learning patch-level forensic signatures and quantifying their distributional discrepancies with MMD, yielding larger separation than global methods when micro-defects are present.
Researchers train AI detectors on a large photorealistic fake image dataset, apply 16 XAI methods, and use human survey feedback to assess alignment between machine explanations and human perception of AI-generated images.
HiMix combines mixup augmentation to create transitional real-fake samples with hierarchical global-local artifact feature fusion to achieve better generalization in detecting AI-generated images from unseen generators.
FGINet uses a band-masked frequency encoder and layer-wise gated injection to fuse frequency artifacts with vision foundation model semantics, plus hyperspherical compactness learning, to achieve better generalization in AI-generated image detection.
Modern vision foundation models plus a tunable attention pooling classifier head deliver state-of-the-art detection of AI-generated and inpainted images, outperforming CLIP by over 12 percent accuracy.
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.
citing papers explorer
-
Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection
ForeAgent combines a Perception-Verdict MLLM architecture with hindsight-driven self-refining via sampling-reflection-evolution to reach 82.18% accuracy on Chameleon and 93.3% mean accuracy across 16 generators on AIGCDetect-Benchmark.
-
Impostor: An Agent-Curated Benchmark for Realistic AIGC Manipulation Localization
Introduces the Impostor benchmark dataset for localizing AIGC image manipulations via agent curation and the PANet model that uses phase and semantic consistency for better detection.
-
FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection
FiSeR uses coarse contrastive separation of natural vs synthetic images plus fine contrastive grouping by generator identity to improve cross-domain AUROC by +10.22 over DIRE baseline on multiple test sets.
-
Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection
PROBE improves AIGI detector generalization to unseen generators by using the detector as a critic to steer manifold-level modifications that produce challenging training samples.
-
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.
-
ImageAttributionBench: How Far Are We from Generalizable Attribution?
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
-
LEGO: LoRA-Enabled Generator-Oriented Framework for Synthetic Image Detection
LEGO uses multiple generator-specific LoRA modules modulated by an MLP and fused with attention to detect synthetic images, achieving better performance than prior methods while using under 10% of the training data.
-
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.
-
ForensicConcept: Transferable Forensic Concepts for AIGI Detection
ForensicConcept extracts and transfers forensic concepts from AIGI detectors via Transformer attribution, concept codebooks, CleanDIFT references, and CKNNA alignment to improve detection on unseen generators.
-
DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities
DetectZoo is a unified toolkit providing reference implementations of 61 detectors, native loaders for 22 benchmark datasets, and a standardized evaluation pipeline for AI-generated content detection across text, audio, and image modalities.
-
Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images
Color transformations expose statistical discrepancies in synthetic images, supporting a classifier with 93.27% average accuracy and robustness to post-processing.
-
CoDA: Color Distribution Probing for Efficient and Generalizable AI-Generated Image Detection
CoDA is a lightweight detector using a Noise-Quantization Probe on color non-uniformity that reports strong cross-domain results on the new FakeForm benchmark and competitive cross-model performance on standard tests.
-
Spectral Tail Auxiliary Learning for AI-Generated Image Detection
STAL transfers spectral tail uplift cues via a frequency teacher to train a spatial detector for AI-generated images, discarding frequency modules at inference for strong cross-generator generalization.
-
Deepfake Detection Generalization with Diffusion Noise
ANL uses diffusion noise prediction and attention to regularize deepfake detectors for better generalization to unseen synthesis methods without added inference cost.
-
PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detection
PGC introduces peak-focusing aggregation of local discriminative clues to calibrate global representations for AI-generated image detection, reporting accuracy gains on a new 15-model commercial benchmark and standard datasets.
-
Venus-DeFakerOne: Unified Fake Image Detection & Localization
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
-
Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
MDMF detects AI-generated images by learning patch-level forensic signatures and quantifying their distributional discrepancies with MMD, yielding larger separation than global methods when micro-defects are present.
-
AI-Generated Images: What Humans and Machines See When They Look at the Same Image
Researchers train AI detectors on a large photorealistic fake image dataset, apply 16 XAI methods, and use human survey feedback to assess alignment between machine explanations and human perception of AI-generated images.
-
HiMix: Hierarchical Artifact-aware Mixup for Generalized Synthetic Image Detection
HiMix combines mixup augmentation to create transitional real-fake samples with hierarchical global-local artifact feature fusion to achieve better generalization in detecting AI-generated images from unseen generators.
-
Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detection
FGINet uses a band-masked frequency encoder and layer-wise gated injection to fuse frequency artifacts with vision foundation model semantics, plus hyperspherical compactness learning, to achieve better generalization in AI-generated image detection.
-
TAP into the Patch Tokens: Leveraging Vision Foundation Model Features for AI-Generated Image Detection
Modern vision foundation models plus a tunable attention pooling classifier head deliver state-of-the-art detection of AI-generated and inpainted images, outperforming CLIP by over 12 percent accuracy.
-
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.
-
SPECTRA-Net: Scalable Pipeline for Explainable Cross-domain Tensor Representations for AI-generated Images Detection
SPECTRA-Net fuses multi-view tensor representations from vision foundation models, spectral analysis, local anomaly detection, and statistical descriptors to achieve state-of-the-art cross-domain AI-generated image detection with explainable artifact localization.
-
Adaptive Forensic Feature Refinement via Intrinsic Importance Perception
I2P adaptively selects the most discriminative layers from visual foundation models for synthetic image detection and constrains task updates to low-sensitivity parameter subspaces to improve specificity without harming generalization.
-
Face-D(^2)CL: Multi-Domain Synergistic Representation with Dual Continual Learning for Facial DeepFake Detection
Face-D²CL fuses spatial and frequency features and uses dual continual learning to reduce forgetting while adapting to new DeepFakes, cutting average error rates by 60.7% and raising unseen-domain AUC by 7.9% over prior SOTA.
-
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.
-
Deepfakes: we need to re-think the concept of "real" images
This position paper contends that the concept of 'real' images must be rethought because most modern photographs are computationally generated, undermining current deepfake detection methods.
-
Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges
A systematic review of fully AI-generated image detection that organizes prior work around dataset construction and artifact extraction methods based on inductive priors.