Deepfake Detection via Knowledge Injection

• URL: http://arxiv.org/abs/2503.02503v1
• Date: Tue, 04 Mar 2025 11:11:14 GMT
• Title: Deepfake Detection via Knowledge Injection
• Authors: Tonghui Li, Yuanfang Guo, Zeming Liu, Heqi Peng, Yunhong Wang,
• Abstract summary: Existing deepfake detection methods tend to overlook the essential role of real data knowledge.<n>A knowledge injection module is proposed to learn and inject necessary knowledge into the backbone model.<n>Two layer-wise suppression and contrast losses are proposed to emphasize the knowledge of real data in the knowledge injection module.
• Score: 35.95604525443886
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deepfake detection technologies become vital because current generative AI models can generate realistic deepfakes, which may be utilized in malicious purposes. Existing deepfake detection methods either rely on developing classification methods to better fit the distributions of the training data, or exploiting forgery synthesis mechanisms to learn a more comprehensive forgery distribution. Unfortunately, these methods tend to overlook the essential role of real data knowledge, which limits their generalization ability in processing the unseen real and fake data. To tackle these challenges, in this paper, we propose a simple and novel approach, named Knowledge Injection based deepfake Detection (KID), by constructing a multi-task learning based knowledge injection framework, which can be easily plugged into existing ViT-based backbone models, including foundation models. Specifically, a knowledge injection module is proposed to learn and inject necessary knowledge into the backbone model, to achieve a more accurate modeling of the distributions of real and fake data. A coarse-grained forgery localization branch is constructed to learn the forgery locations in a multi-task learning manner, to enrich the learned forgery knowledge for the knowledge injection module. Two layer-wise suppression and contrast losses are proposed to emphasize the knowledge of real data in the knowledge injection module, to further balance the portions of the real and fake knowledge. Extensive experiments have demonstrated that our KID possesses excellent compatibility with different scales of Vit-based backbone models, and achieves state-of-the-art generalization performance while enhancing the training convergence speed.

Related papers

• Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning [60.01714908976762]
  This paper proposes a four-tier knowledge injection framework that defines the levels of knowledge injection: memorization, retrieval, reasoning, and association. We then explore various knowledge injection scenarios and evaluate the depth of knowledge injection for each scenario on the benchmark.
  arXiv  Detail & Related papers  (2025-04-01T06:59:59Z)
• What Really Matters for Learning-based LiDAR-Camera Calibration [50.2608502974106]
  This paper revisits the development of learning-based LiDAR-Camera calibration. We identify the critical limitations of regression-based methods with the widely used data generation pipeline. We also investigate how the input data format and preprocessing operations impact network performance.
  arXiv  Detail & Related papers  (2025-01-28T14:12:32Z)
• Exploiting Diffusion Prior for Out-of-Distribution Detection [11.11093497717038]
  Out-of-distribution (OOD) detection is crucial for deploying robust machine learning models. We present a novel approach for OOD detection that leverages the generative ability of diffusion models and the powerful feature extraction capabilities of CLIP.
  arXiv  Detail & Related papers  (2024-06-16T23:55:25Z)
• CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition [53.860796916196634]
  We propose a Deep Information Decomposition (DID) framework to enhance the performance of Cross-dataset Deepfake Detection (CrossDF) Unlike most existing deepfake detection methods, our framework prioritizes high-level semantic features over specific visual artifacts. It adaptively decomposes facial features into deepfake-related and irrelevant information, only using the intrinsic deepfake-related information for real/fake discrimination.
  arXiv  Detail & Related papers  (2023-09-30T12:30:25Z)
• Plug-and-Play Knowledge Injection for Pre-trained Language Models [116.37916535076478]
  Injecting external knowledge can improve the performance of pre-trained language models (PLMs) on various downstream NLP tasks. Massive retraining is required to deploy new knowledge injection methods or knowledge bases for downstream tasks. We study how to improve the flexibility and efficiency of knowledge injection by reusing existing downstream models.
  arXiv  Detail & Related papers  (2023-05-28T10:58:00Z)
• Neuro-symbolic model for cantilever beams damage detection [0.0]
  We propose a neuro-symbolic model for the detection of damages in cantilever beams based on a novel cognitive architecture. The hybrid discriminative model is introduced under the name Logic Convolutional Neural Regressor.
  arXiv  Detail & Related papers  (2023-05-04T13:12:39Z)
• Principled Knowledge Extrapolation with GANs [92.62635018136476]
  We study counterfactual synthesis from a new perspective of knowledge extrapolation. We show that an adversarial game with a closed-form discriminator can be used to address the knowledge extrapolation problem. Our method enjoys both elegant theoretical guarantees and superior performance in many scenarios.
  arXiv  Detail & Related papers  (2022-05-21T08:39:42Z)
• Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillation [51.66271681532262]
  Online Self-Acquired Knowledge Distillation (OSAKD) is proposed, aiming to improve the performance of any deep neural model in an online manner. We utilize k-nn non-parametric density estimation technique for estimating the unknown probability distributions of the data samples in the output feature space.
  arXiv  Detail & Related papers  (2021-08-26T14:01:04Z)
• FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning [17.97648576135166]
  We introduce a transfer learning-based Feature Representation Transfer Adaptation Learning (FReTAL) method. Our student model can quickly adapt to new types of deepfake by distilling knowledge from a pre-trained teacher model. FReTAL outperforms all baselines on the domain adaptation task with up to 86.97% accuracy on low-quality deepfakes.
  arXiv  Detail & Related papers  (2021-05-28T06:54:10Z)

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.