V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors

• URL: http://arxiv.org/abs/2608.03008v1
• Date: Tue, 04 Aug 2026 01:41:40 GMT
• Title: V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors
• Abstract summary: We find that forgery-discriminative knowledge is not uniformly distributed across the full representation space.<n>We propose a video forgery-intrinsic neuron discovery framework (V-FIND)<n>V-FIND localizes critical layers that exhibit pronounced discrepancies between real and forged videos, and then identifies latent anchor neurons that consistently carry forgery-discriminative signals.
• Score: 64.12551408538918
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors as black boxes, while the latent forgery-discriminative knowledge inside them remains largely unexplored. Instead of continuing to rely on resource-intensive full-model retraining to steadily improve detection performance, we ask whether video forgery detection can also be achieved by uncovering and activating sparse forensic knowledge within the detector. We find that forgery-discriminative knowledge is not uniformly distributed across the full representation space, but is concentrated in a sparse set of functionally specialized neurons. Based on this insight, we propose a video forgery-intrinsic neuron discovery (V-FIND) framework. V-FIND first localizes critical layers that exhibit pronounced discrepancies between real and forged videos, and then identifies latent anchor neurons that consistently carry forgery-discriminative signals, organizing them into a compact forensic subspace. With the original backbone frozen and only a lightweight linear classifier trained, this subspace still delivers strong detection performance across multiple external benchmarks for generated videos. Further neuron intervention experiments provide direct evidence for the functional specificity of the discovered neurons. Overall, these results suggest that video forgery detectors contain sparse, extractable, and reusable forgery-discriminative knowledge, offering a new perspective on understanding and exploiting their intrinsic forensic capability.

Related papers

• Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models [40.6282934670186]
  We argue that anomaly knowledge is intrinsically embedded within pre-trained models but remains latent and under-activated.<n>We propose latent anomaly knowledge excavation (LAKE), a training-free framework that identifies and elicits these critical neuronal signals.<n>Our work advocates for a paradigm shift: redefining anomaly detection as the targeted activation of latent pre-trained knowledge.
  arXiv  Detail & Related papers  (2026-04-09T04:54:25Z)
• DNA: Uncovering Universal Latent Forgery Knowledge [39.19379714306656]
  forgery detection capability is already encoded within pre-trained models.<n>DNA framework employs a coarse-to-fine excavation mechanism.<n>Hifi-Gen is a high-fidelity synthetic benchmark built upon the very latest models.
  arXiv  Detail & Related papers  (2026-01-30T03:48:30Z)
• Rethinking Cross-Generator Image Forgery Detection through DINOv3 [62.80415066351157]
  Cross-generator detection has emerged as a new challenge forgenerative models.<n>We show that frozen visual foundation models, especially DINOv3, already exhibit strong cross-generator detection capability.<n>We introduce a training-free token-ranking strategy followed by a lightweight linear probe to select a small subset of authenticity-relevant tokens.
  arXiv  Detail & Related papers  (2025-11-27T14:01:50Z)
• ED$^4$: Explicit Data-level Debiasing for Deepfake Detection [24.695989108814018]
  Learning intrinsic bias from limited data has been considered the main reason for the failure of deepfake detection with generalizability.<n>We present ED$4$, a simple and effective strategy to address aforementioned biases explicitly at the data level.<n>We conduct extensive experiments to demonstrate its effectiveness and superiority over existing deepfake detection approaches.
  arXiv  Detail & Related papers  (2024-08-13T10:05:20Z)
• Latent Spatiotemporal Adaptation for Generalized Face Forgery Video Detection [22.536129731902783]
  We propose a Latemporal Spatio(LAST) approach to facilitate generalized face video detection. We first model thetemporal patterns face videos by incorporating a lightweight CNN to extract local spatial features of each frame. Then we learn the long-termtemporal representations in latent space videos, which should contain more clues than in pixel space.
  arXiv  Detail & Related papers  (2023-09-09T13:40:44Z)
• Spatial-Frequency Discriminability for Revealing Adversarial Perturbations [53.279716307171604]
  Vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. Current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. We propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition.
  arXiv  Detail & Related papers  (2023-05-18T10:18:59Z)
• Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [122.4894940892536]
  We present a novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level. In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss.
  arXiv  Detail & Related papers  (2022-09-25T04:56:10Z)
• Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams [64.82800502603138]
  This paper proposes a novel neural-network-based approach to progressively and autonomously develop pixel-wise representations in a video stream. The proposed method is based on a human-like attention mechanism that allows the agent to learn by observing what is moving in the attended locations. Our experiments leverage 3D virtual environments and they show that the proposed agents can learn to distinguish objects just by observing the video stream.
  arXiv  Detail & Related papers  (2022-04-26T09:52:31Z)
• PAT: Pseudo-Adversarial Training For Detecting Adversarial Videos [20.949656274807904]
  We propose a novel yet simple algorithm called Pseudo-versa-Adrial Training (PAT) to detect the adversarial frames in a video without requiring knowledge of the attack. Experimental results on UCF-101 and 20BN-Jester datasets show that PAT can detect the adversarial video frames and videos with a high detection rate.
  arXiv  Detail & Related papers  (2021-09-13T04:05:46Z)
• BiDet: An Efficient Binarized Object Detector [96.19708396510894]
  We propose a binarized neural network learning method called BiDet for efficient object detection. Our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal. Our method outperforms the state-of-the-art binary neural networks by a sizable margin.
  arXiv  Detail & Related papers  (2020-03-09T08:16:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.