Unleashing Vision-Language Semantics for Deepfake Video Detection

• URL: http://arxiv.org/abs/2603.24454v1
• Date: Wed, 25 Mar 2026 16:05:35 GMT
• Title: Unleashing Vision-Language Semantics for Deepfake Video Detection
• Abstract summary: Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) exhibit strong generalization capabilities in detecting artifacts across different identities.<n>We propose VLAForge, a novel DFD framework that unleashes the potential of such cross-modal semantics to enhance model's discriminability in deepfake detection.
• Score: 78.7562836979696
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) such as CLIP exhibit strong generalization capabilities in detecting artifacts across different identities. However, existing approaches focus on leveraging visual features only, overlooking their most distinctive strength -- the rich vision-language semantics embedded in the latent space. We propose VLAForge, a novel DFD framework that unleashes the potential of such cross-modal semantics to enhance model's discriminability in deepfake detection. This work i) enhances the visual perception of VLM through a ForgePerceiver, which acts as an independent learner to capture diverse, subtle forgery cues both granularly and holistically, while preserving the pretrained Vision-Language Alignment (VLA) knowledge, and ii) provides a complementary discriminative cue -- Identity-Aware VLA score, derived by coupling cross-modal semantics with the forgery cues learned by ForgePerceiver. Notably, the VLA score is augmented by an identity prior-informed text prompting to capture authenticity cues tailored to each identity, thereby enabling more discriminative cross-modal semantics. Comprehensive experiments on video DFD benchmarks, including classical face-swapping forgeries and recent full-face generation forgeries, demonstrate that our VLAForge substantially outperforms state-of-the-art methods at both frame and video levels. Code is available at https://github.com/mala-lab/VLAForge.

Related papers

• LaCoVL-FER: Landmark-Guided Contrastive Learning Network with Vision-Language Enhancement for Facial Expression Recognition [51.70817823155725]
  We propose a novel landmark-guided contrastive learning network with vision-language enhancement for Facial Expression Recognition (FER)<n>LaCoVL-FER integrates geometric priors from facial landmarks and semantic priors from a vision-language model.<n>Experiments demonstrate that LaCoVL-FER outperforms state-of-the-art methods on three representative real-world FER datasets.
  arXiv  Detail & Related papers  (2026-05-19T13:15:41Z)
• Enhancing Open-Vocabulary Object Detection through Multi-Level Fine-Grained Visual-Language Alignment [14.066865082355696]
  Open-vocabulary object detection (OVD) enables the identification of objects from novel classes not present in the training set.<n>Recent advances in visual-language modeling have led to significant progress of OVD.<n>We propose Visual-Language Detection (VLDet), a novel framework that revamps feature pyramid for fine-grained visual-language alignment.
  arXiv  Detail & Related papers  (2026-01-31T05:51:45Z)
• Attention Guided Alignment in Efficient Vision-Language Models [56.20286899428444]
  Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs)<n>This paper presents a comprehensive analysis of attention patterns in efficient VLMs.<n>We introduce Attention-Guided Efficient Vision-Language Models (AGE-VLM), a novel framework that enhances visual grounding through interleaved cross-attention layers.
  arXiv  Detail & Related papers  (2025-11-21T21:36:48Z)
• VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set [80.50996301430108]
  The alignment of vision-language representations endows current Vision-Language Models with strong multi-modal reasoning capabilities.<n>We propose VL-SAE, a sparse autoencoder that encodes vision-language representations into its hidden activations.<n>For interpretation, the alignment between vision and language representations can be understood by comparing their semantics with concepts.
  arXiv  Detail & Related papers  (2025-10-24T10:29:31Z)
• HAMLET-FFD: Hierarchical Adaptive Multi-modal Learning Embeddings Transformation for Face Forgery Detection [6.060036926093259]
  HAMLET-FFD is a cross-domain generalization framework for face forgery detection.<n>It integrates visual evidence with conceptual cues, emulating expert forensic analysis.<n>By design, HAMLET-FFD freezes all pretrained parameters, serving as an external plugin.
  arXiv  Detail & Related papers  (2025-07-28T15:09:52Z)
• SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding [5.976839106353883]
  SECOND: Selective and Contrastive Decoding is a novel approach that enables Vision-Language Models to leverage multi-scale visual information with an object-centric manner.<n> SECOND significantly reduces perceptual hallucinations and outperforms a wide range of benchmarks.
  arXiv  Detail & Related papers  (2025-06-10T02:55:38Z)
• MLLM-Enhanced Face Forgery Detection: A Vision-Language Fusion Solution [36.79921476565535]
  VLF-FFD is a novel Vision-Language Fusion solution for MLLM-enhanced Face Forgery Detection.<n> EFF++ is a frame-level, explainability-driven extension of the widely used FaceForensics++ dataset.<n>VLF-FFD achieves state-of-the-art (SOTA) performance in both cross-dataset and intra-dataset evaluations.
  arXiv  Detail & Related papers  (2025-05-04T06:58:21Z)
• PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution [36.409362073662685]
  We propose a novel parsing-aware vision language model with dynamic contrastive learning (PVLM) method for zero-shot deepfake attribution (ZS-DFA)<n>Specifically, we conduct a novel and fine-grained ZS-DFA benchmark to evaluate the attribution performance of deepfake attributors to unseen advanced generators like diffusion.<n>We also propose an innovative parsing-guided vision language model with dynamic contrastive learning (PVLM) method to capture general and diverse attribution features.
  arXiv  Detail & Related papers  (2025-04-19T01:11:46Z)
• Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection [18.125287697902813]
  Current Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in understanding multimodal data.<n>We present a novel framework that unlocks LVLMs' potential capabilities for deepfake detection.
  arXiv  Detail & Related papers  (2025-03-19T03:20:03Z)
• MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection [107.15164718585666]
  We investigate the root cause of VLMs' biased prediction under the open vocabulary detection context. Our observations lead to a simple yet effective paradigm, coded MarvelOVD, that generates significantly better training targets. Our method outperforms the other state-of-the-arts by significant margins.
  arXiv  Detail & Related papers  (2024-07-31T09:23:57Z)
• SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning [51.800031281177105]
  SignVTCL is a continuous sign language recognition framework enhanced by visual-textual contrastive learning. It integrates multi-modal data (video, keypoints, and optical flow) simultaneously to train a unified visual backbone. It achieves state-of-the-art results compared with previous methods.
  arXiv  Detail & Related papers  (2024-01-22T11:04:55Z)
• SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification [84.05253637260743]
  We propose a new framework, named Semantic-guided Visual Adapting (SgVA), to extend vision-language pre-trained models. SgVA produces discriminative task-specific visual features by comprehensively using a vision-specific contrastive loss, a cross-modal contrastive loss, and an implicit knowledge distillation. State-of-the-art results on 13 datasets demonstrate that the adapted visual features can well complement the cross-modal features to improve few-shot image classification.
  arXiv  Detail & Related papers  (2022-11-28T14:58:15Z)

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.