Pith. sign in

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

arxiv 2406.09398 v1 pith:LVAREPTU submitted 2024-06-13 cs.CV

Real-Time Deepfake Detection in the Real-World

classification cs.CV
keywords deepfakedetectionladedareal-worldscoreaccuracycurrentimage
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection

    cs.CV 2026-05 unverdicted novelty 7.0

    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.

  2. LEGO: LoRA-Enabled Generator-Oriented Framework for Synthetic Image Detection

    cs.CV 2026-05 unverdicted novelty 7.0

    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.

  3. Automated In-the-Wild Data Collection for Continual AI Generated Image Detection

    cs.CV 2026-05 unverdicted novelty 7.0

    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...

  4. VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection

    cs.CV 2026-03 conditional novelty 6.5

    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.

  5. Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection

    cs.CV 2026-07 conditional novelty 6.0

    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.

  6. GlobalForge: Towards Robust AI-Generated Image Detection

    cs.CV 2026-07 conditional novelty 6.0

    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...

  7. Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection

    cs.CV 2026-07 unverdicted novelty 6.0

    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.

  8. TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images

    cs.CV 2026-05 unverdicted novelty 6.0

    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.

  9. HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection

    cs.CV 2026-05 unverdicted novelty 6.0

    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.

  10. Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

    cs.CV 2026-05 conditional novelty 6.0

    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.

  11. Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models

    cs.CV 2026-02 conditional novelty 6.0

    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.

  12. How Noise Benefits AI-generated Image Detection

    cs.CV 2025-11 unverdicted novelty 6.0

    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....

  13. Generalized Synthetic Image Detection with Enhanced RGB-Noise Representation Learning

    cs.CV 2026-07 conditional novelty 5.0

    RNSIDNet detects synthetic images by using CLIP RGB features to dynamically modulate Bayar-convolution noise residuals, trained with a hard-sample-aware contrastive loss.

  14. Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection

    cs.CV 2026-06 unverdicted novelty 5.0

    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.

  15. SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders

    cs.CV 2026-06 unverdicted novelty 5.0

    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.

  16. Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection

    cs.CV 2026-05 unverdicted novelty 5.0

    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.

  17. PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detection

    cs.CV 2026-05 unverdicted novelty 5.0

    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...

  18. Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts

    cs.CV 2026-05 unverdicted novelty 5.0

    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.

  19. Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detection

    cs.CV 2026-04 unverdicted novelty 5.0

    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...

  20. Deepfake Detection in Social Media: A Temporal Artifact Analysis Using 3D Convolutional Neural Networks

    cs.CV 2026-05 unverdicted novelty 4.0

    3D CNN detector with temporal consistency regularizer reaches 92.8% accuracy on DeepfakeTIMIT and 76.4% cross-dataset on FaceForensics++ without fine-tuning.

  21. SPECTRA-Net: Scalable Pipeline for Explainable Cross-domain Tensor Representations for AI-generated Images Detection

    cs.CV 2026-05 unverdicted novelty 4.0

    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...

  22. HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild

    cs.CV 2026-04 unverdicted novelty 4.0

    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...

  23. Deepfakes: we need to re-think the concept of "real" images

    cs.CV 2025-09 unverdicted novelty 4.0

    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.