Pith. sign in

REVIEW 13 cited by

Real-Time Deepfake Detection in the Real-World

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

Bar Cavia , Eliahu Horwitz , Tal Reiss , Yedid Hoshen This is my paper · ORCID
classification cs.CV
keywords deepfakedetectionladedareal-worldscoreaccuracycurrentimage
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

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). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

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

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

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    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.

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

    cs.CV 2026-03 conditional novelty 6.5 of 10

    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.

  3. LHSDet: High-Resolution AI-Generated Image Detection via Visual Question Answering

    cs.CV 2026-08 conditional novelty 6.0 of 10

    LHSDet detects AI-generated images by fusing low-level texture features, SigLIP2 global features, and BLIP-2 captions in a visual question answering framework, reaching 96% average cross-model accuracy.

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

    cs.CV 2026-07 conditional novelty 6.0 of 10

    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.

  5. GlobalForge: Towards Robust AI-Generated Image Detection

    cs.CV 2026-07 conditional novelty 6.0 of 10

    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...

  6. Continuously Evolving Deepfake Detection: An Architecture and Public-Benchmark Evaluation of a Dynamic Detection System

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A continuously refreshed, incentive-driven deepfake detector beats static detectors on in-the-wild benchmarks and improves on post-export AI-generated media.

  7. Sliced Transport Plans

    math.OC 2025-08 unverdicted novelty 6.0 of 10

    A new sliced-Wasserstein-based discrepancy with provable semi-metric properties and a constrained Kantorovich relation, plus a generic-measure generalization of Expected Sliced plans.

  8. A Bias-Free Training Paradigm for More General AI-generated Image Detection

    cs.CV 2024-12 conditional novelty 6.0 of 10

    B-Free trains an AI-image detector on self-conditioned Stable Diffusion 2.1 reconstructions of COCO photos plus inpainting-based augmentation, improving generalization to unseen generators and calibration.

  9. PatchHead: Learning Spatial Patch Evidence for Generalizable AI-Generated Image Detection

    cs.CV 2026-08 conditional novelty 5.0 of 10

    Classifying from spatially aggregated DINO patch tokens instead of a single CLS token improves cross-dataset AI-generated image detection by about three percentage points average balanced accuracy.

  10. Unleashing the Potential of Vision-Language Models for Generalizable AI-Generated Image Detection

    cs.CV 2026-08 conditional novelty 5.0 of 10

    Initializing a frozen vision-language encoder's linear probe with text-derived prototypes ('AI art' vs 'a real photo') and calibrating on one source improves cross-generator, in-the-wild, and post-processing AI-genera...

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

    cs.CV 2026-07 conditional novelty 5.0 of 10

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

  12. A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection

    cs.CV 2025-08 conditional novelty 5.0 of 10

    SFMFNet uses wavelet-frequency gating, token-selective cross-attention, and blur pooling to reach 0.8682 average cross-dataset AUC with only 1.27 GFLOPs and 6.64M parameters.

  13. Nearly Solved? Robust Deepfake Detection Requires More than Visual Forensics

    cs.CV 2024-12 reject novelty 5.0 of 10

    Black-box genetic attacks flip 70% of correct fake detections in a retrained patch-based detector, GPT-4o reaches 73% AUC zero-shot on a Celeb-DF subset, and a 6.64% typographic attack degrades it.

Pith tools