REVIEW 23 cited by
Real-Time Deepfake Detection in the Real-World
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Real-Time Deepfake Detection in the Real-World
read the original abstract
Recent improvements in generative AI made synthesizing fake images easy; as they can be used to cause harm, it is crucial to develop accurate techniques to identify them. This paper introduces "Locally Aware Deepfake Detection Algorithm" (LaDeDa), that accepts a single 9x9 image patch and outputs its deepfake score. The image deepfake score is the pooled score of its patches. With merely patch-level information, LaDeDa significantly improves over the state-of-the-art, achieving around 99% mAP on current benchmarks. Owing to the patch-level structure of LaDeDa, we hypothesize that the generation artifacts can be detected by a simple model. We therefore distill LaDeDa into Tiny-LaDeDa, a highly efficient model consisting of only 4 convolutional layers. Remarkably, Tiny-LaDeDa has 375x fewer FLOPs and is 10,000x more parameter-efficient than LaDeDa, allowing it to run efficiently on edge devices with a minor decrease in accuracy. These almost-perfect scores raise the question: is the task of deepfake detection close to being solved? Perhaps surprisingly, our investigation reveals that current training protocols prevent methods from generalizing to real-world deepfakes extracted from social media. To address this issue, we introduce WildRF, a new deepfake detection dataset curated from several popular social networks. Our method achieves the top performance of 93.7% mAP on WildRF, however the large gap from perfect accuracy shows that reliable real-world deepfake detection is still unsolved.
Forward citations
Cited by 23 Pith papers
-
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.
-
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.
-
Automated In-the-Wild Data Collection for Continual AI Generated Image Detection
An automated fact-check-based pipeline for in-the-wild AI image data, when mixed with generator data in continual learning, lets detectors adapt to new generators while avoiding forgetting and delivers 8-9% accuracy g...
-
VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection
A plan-then-examine MLLM framework with stage-gated part-level forensic injection and part-aware RL rewards outperforms expert and concurrent MLLM deepfake detectors across a hierarchical 5-level generalizability benchmark.
-
Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection
Strengthening fine-grained, semantic-anomaly, and pixel-level perception with verifiable rewards, then value-aware on-policy self-distillation, improves generalizable MLLM AI-image detection and adaptation.
-
GlobalForge: Towards Robust AI-Generated Image Detection
GlobalForge improves AI-generated image detection under real-world degradation by suppressing local shortcuts and enforcing long-range structural reasoning, outperforming prior state-of-the-art by 5.89% average balanc...
-
Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection
Motion-based AI video detectors exploit motion biases in evaluation datasets and drop to near-random performance on rebalanced data, while frequency-based detectors remain robust.
-
TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images
TextFake benchmark shows no AI-generated image detector exceeds 80% accuracy on text-rich images and identifies three failure modes including text density and rendering fidelity issues.
-
HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection
HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.
-
Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection
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.
-
Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models
Frozen features from vision foundation models enable a linear probe to outperform specialized AIGI detectors by over 30% on in-the-wild data due to emergent forgery knowledge from pre-training.
-
How Noise Benefits AI-generated Image Detection
PiN-CLIP jointly trains a noise generator and detector under a variational positive-incentive principle to inject feature-space noise that suppresses shortcut directions and improves out-of-distribution accuracy by 5....
-
Generalized Synthetic Image Detection with Enhanced RGB-Noise Representation Learning
RNSIDNet detects synthetic images by using CLIP RGB features to dynamically modulate Bayar-convolution noise residuals, trained with a hard-sample-aware contrastive loss.
-
Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection
DEAR prunes channel features whose activations align strongly with inpaint masks, retaining only those capturing genuine generative artifacts to improve robustness against post-processing and unseen generators.
-
SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders
Frozen multimodal encoders enable robust AI-generated image detection via linear classification on a 10K-image curated training set that improves generalization over larger datasets.
-
Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection
VINA trains a single detector on images plus video frames using a cross-modal supervised contrastive objective, yielding bidirectional gains and SOTA results on 14 image, video, and in-the-wild benchmarks.
-
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...
-
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.
-
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...
-
Deepfake Detection in Social Media: A Temporal Artifact Analysis Using 3D Convolutional Neural Networks
3D CNN detector with temporal consistency regularizer reaches 92.8% accuracy on DeepfakeTIMIT and 76.4% cross-dataset on FaceForensics++ without fine-tuning.
-
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 de...
-
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...
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.