Unlocking the Hidden Potential of CLIP in Generalizable Deepfake Detection

• URL: http://arxiv.org/abs/2503.19683v2
• Date: Wed, 26 Mar 2025 11:21:23 GMT
• Title: Unlocking the Hidden Potential of CLIP in Generalizable Deepfake Detection
• Authors: Andrii Yermakov, Jan Cech, Jiri Matas,
• Abstract summary: This paper tackles the challenge of detecting partially manipulated facial deepfakes.<n>We leverage the Contrastive Language-Image Pre-training (CLIP) model, specifically its ViT-L/14 visual encoder.<n>The proposed approach utilizes parameter-efficient fine-tuning (PEFT) techniques, such as LN-tuning, to adjust a small subset of the model's parameters.
• Score: 23.48106270102081
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper tackles the challenge of detecting partially manipulated facial deepfakes, which involve subtle alterations to specific facial features while retaining the overall context, posing a greater detection difficulty than fully synthetic faces. We leverage the Contrastive Language-Image Pre-training (CLIP) model, specifically its ViT-L/14 visual encoder, to develop a generalizable detection method that performs robustly across diverse datasets and unknown forgery techniques with minimal modifications to the original model. The proposed approach utilizes parameter-efficient fine-tuning (PEFT) techniques, such as LN-tuning, to adjust a small subset of the model's parameters, preserving CLIP's pre-trained knowledge and reducing overfitting. A tailored preprocessing pipeline optimizes the method for facial images, while regularization strategies, including L2 normalization and metric learning on a hyperspherical manifold, enhance generalization. Trained on the FaceForensics++ dataset and evaluated in a cross-dataset fashion on Celeb-DF-v2, DFDC, FFIW, and others, the proposed method achieves competitive detection accuracy comparable to or outperforming much more complex state-of-the-art techniques. This work highlights the efficacy of CLIP's visual encoder in facial deepfake detection and establishes a simple, powerful baseline for future research, advancing the field of generalizable deepfake detection. The code is available at: https://github.com/yermandy/deepfake-detection

Related papers

• Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detections [50.343419243749054]
  Anomaly Detection (AD) involves identifying deviations from normal data distributions. We propose a novel approach that conditions the prompts of the text encoder based on image context extracted from the vision encoder. Our method achieves state-of-the-art performance, improving performance by 2% to 29% across different metrics on 14 datasets.
  arXiv  Detail & Related papers  (2025-04-15T10:42:25Z)
• Deepfake Detection with Optimized Hybrid Model: EAR Biometric Descriptor via Improved RCNN [1.1356542363919058]
  We introduce robust detection of subtle ear movements and shape changes to generate ear descriptors. We also propose a novel optimized hybrid deepfake detection model that considers the ear biometric descriptors via enhanced RCNN. Our proposed method outperforms traditional models such as CNN (Convolution Neural Network), SqueezeNet, LeNet, LinkNet, LSTM (Long Short-Term Memory), DFP (Deepfake Predictor), and ResNext+CNN+LSTM.
  arXiv  Detail & Related papers  (2025-03-16T07:01:29Z)
• Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detection [0.0]
  Wavelet-CLIP is a deepfake detection framework that integrates wavelet transforms with features derived from the ViT-L/14 architecture, pre-trained in the CLIP fashion.<n>Our method showcases outstanding performance, achieving an average AUC of 0.749 for cross-data generalization and 0.893 for robustness against unseen deepfakes.
  arXiv  Detail & Related papers  (2024-09-26T21:16:51Z)
• Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection [16.21235742118949]
  We propose a novel approach that repurposes a well-trained Vision-Language Models (VLMs) for general deepfake detection.<n>Motivated by the model reprogramming paradigm that manipulates the model prediction via input perturbations, our method can reprogram a pre-trained VLM model.<n>Experiments on several popular benchmark datasets demonstrate that the cross-dataset and cross-manipulation performances of deepfake detection can be significantly and consistently improved.
  arXiv  Detail & Related papers  (2024-09-04T12:46:30Z)
• Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture [58.60915132222421]
  We introduce an approach that is both general and parameter-efficient for face forgery detection. We design a forgery-style mixture formulation that augments the diversity of forgery source domains. We show that the designed model achieves state-of-the-art generalizability with significantly reduced trainable parameters.
  arXiv  Detail & Related papers  (2024-08-23T01:53:36Z)
• UniForensics: Face Forgery Detection via General Facial Representation [60.5421627990707]
  High-level semantic features are less susceptible to perturbations and not limited to forgery-specific artifacts, thus having stronger generalization. We introduce UniForensics, a novel deepfake detection framework that leverages a transformer-based video network, with a meta-functional face classification for enriched facial representation.
  arXiv  Detail & Related papers  (2024-07-26T20:51:54Z)
• Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model [16.69101880602321]
  We propose a novel side-network-based decoder for generalized video-based Deepfake detection.<n>We also introduce Facial Component Guidance (FCG) to enhance spatial learning generalizability.<n>Our approach demonstrates promising generalizability on challenging Deepfake datasets.
  arXiv  Detail & Related papers  (2024-04-08T14:58:52Z)
• CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection [3.849401956130233]
  We explore the effectiveness of pre-trained vision-language models (VLMs) when paired with recent adaptation methods for universal deepfake detection. We employ only a single dataset (ProGAN) in order to adapt CLIP for deepfake detection. The simple and lightweight Prompt Tuning based adaptation strategy outperforms the previous SOTA approach by 5.01% mAP and 6.61% accuracy.
  arXiv  Detail & Related papers  (2024-02-20T11:26:42Z)
• 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)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes [7.553507857251396]
  We propose a novel deepfake detector, called SeeABLE, that formalizes the detection problem as a (one-class) out-of-distribution detection task. SeeABLE pushes perturbed faces towards predefined prototypes using a novel regression-based bounded contrastive loss. We show that our model convincingly outperforms competing state-of-the-art detectors, while exhibiting highly encouraging generalization capabilities.
  arXiv  Detail & Related papers  (2022-11-21T09:38:30Z)
• Self-supervised Transformer for Deepfake Detection [112.81127845409002]
  Deepfake techniques in real-world scenarios require stronger generalization abilities of face forgery detectors. Inspired by transfer learning, neural networks pre-trained on other large-scale face-related tasks may provide useful features for deepfake detection. In this paper, we propose a self-supervised transformer based audio-visual contrastive learning method.
  arXiv  Detail & Related papers  (2022-03-02T17:44:40Z)

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.