CAMME: Adaptive Deepfake Image Detection with Multi-Modal Cross-Attention

• URL: http://arxiv.org/abs/2505.18035v1
• Date: Fri, 23 May 2025 15:39:07 GMT
• Title: CAMME: Adaptive Deepfake Image Detection with Multi-Modal Cross-Attention
• Abstract summary: We propose CAMME, a framework that integrates visual, textual, and frequency-domain features through a multi-head cross-attention mechanism.<n>Experiments demonstrate CAMME's superiority over state-of-the-art methods, yielding improvements of 12.56% on natural scenes and 13.25% on facial deepfakes.
• Score: 4.359154048799454
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The proliferation of sophisticated AI-generated deepfakes poses critical challenges for digital media authentication and societal security. While existing detection methods perform well within specific generative domains, they exhibit significant performance degradation when applied to manipulations produced by unseen architectures--a fundamental limitation as generative technologies rapidly evolve. We propose CAMME (Cross-Attention Multi-Modal Embeddings), a framework that dynamically integrates visual, textual, and frequency-domain features through a multi-head cross-attention mechanism to establish robust cross-domain generalization. Extensive experiments demonstrate CAMME's superiority over state-of-the-art methods, yielding improvements of 12.56% on natural scenes and 13.25% on facial deepfakes. The framework demonstrates exceptional resilience, maintaining (over 91%) accuracy under natural image perturbations and achieving 89.01% and 96.14% accuracy against PGD and FGSM adversarial attacks, respectively. Our findings validate that integrating complementary modalities through cross-attention enables more effective decision boundary realignment for reliable deepfake detection across heterogeneous generative architectures.

Related papers

• On Improving Robustness of Deepfake Image Detectors [5.7418146925786795]
  We propose a unified framework that integrates three complementary design principles.<n> adversarial attacks primarily operate on low-order statistics and visual semantics.<n>Our method consistently improves robustness across six architecturally diverse detectors.
  arXiv  Detail & Related papers  (2026-06-01T19:03:32Z)
• CIPHER: Counterfeit Image Pattern High-level Examination via Representation [10.444553810902788]
  We introduce CIPHER, a deepfake detection framework that systematically reuses and fine-tunes discriminators originally trained for image generation.<n>By extracting scale-adaptive features from ProGAN discriminators and temporal-consistency features from diffusion models, CIPHER captures generation-agnostic artifacts that conventional detectors often overlook.
  arXiv  Detail & Related papers  (2026-03-31T07:27:58Z)
• FeatDistill: A Feature Distillation Enhanced Multi-Expert Ensemble Framework for Robust AI-generated Image Detection [14.180599240051238]
  FeatDistill is an AI-generated image detection framework that integrates feature distillation with a multi-expert ensemble.<n>It was developed for the NTIRE Challenge on Robust AI-Generated Image Detection in the Wild.
  arXiv  Detail & Related papers  (2026-03-23T12:55:31Z)
• RCDN: Real-Centered Detection Network for Robust Face Forgery Identification [7.41356813669013]
  Existing detection methods achieve near-perfect performance when training and testing are conducted within the same domain.<n>New forgery techniques continuously emerge and detectors must remain reliable against unseen manipulations.<n>We propose the Real-Centered Detection Network (RCDN), a frequency spatial convolutional neural networks(CNN) framework with an Xception backbone.
  arXiv  Detail & Related papers  (2026-01-17T17:09:15Z)
• ForensicFormer: Hierarchical Multi-Scale Reasoning for Cross-Domain Image Forgery Detection [0.0]
  ForensicFormer is a hierarchical framework that unifies low-level artifact detection, mid-level boundary analysis, and high-level semantic reasoning.<n>Our method maintains 86.8% average accuracy across seven diverse test sets, spanning traditional manipulations, GAN-generated images, and diffusion model outputs.
  arXiv  Detail & Related papers  (2026-01-12T04:29:36Z)
• Patch-Discontinuity Mining for Generalized Deepfake Detection [18.30761992906741]
  Deepfake detection methods often rely on handcrafted forensic cues and complex architectures.<n>We propose GenDF, a framework that transfers a powerful vision model to the deepfake detection task with a compact and neat network design.<n>Experiments demonstrate that GenDF achieves state-of-the-art generalization performance in cross-domain and cross-manipulation settings.
  arXiv  Detail & Related papers  (2025-12-26T13:18:14Z)
• Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation [60.04281435591454]
  CRDA (Curriculum Reinforcement-Learning Data Augmentation) is a novel framework guiding detectors to progressively master multi-domain forgery features.<n>Central to our approach is integrating reinforcement learning and causal inference.<n>Our method significantly improves detector generalizability, outperforming SOTA methods across multiple cross-domain datasets.
  arXiv  Detail & Related papers  (2025-11-10T12:45:52Z)
• A Dual-Branch CNN for Robust Detection of AI-Generated Facial Forgeries [4.313893060699182]
  Face forgery techniques pose significant threats to AI security, digital media integrity, and public trust.<n>We propose a novel dual-branch convolutional neural network for face forgery detection.<n>We evaluate our model on the DiFF benchmark, which includes forged images generated from four representative methods.
  arXiv  Detail & Related papers  (2025-10-28T17:06:40Z)
• Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios [54.07895223545793]
  This paper introduces the Real-World Robustness dataset (RRDataset) for comprehensive evaluation of detection models across three dimensions.<n>RRDataset includes high-quality images from seven major scenarios.<n>We benchmarked 17 detectors and 10 vision-language models (VLMs) on RRDataset and conducted a large-scale human study.
  arXiv  Detail & Related papers  (2025-09-11T06:15:52Z)
• Deep Learning Models for Robust Facial Liveness Detection [56.08694048252482]
  This study introduces a robust solution through novel deep learning models addressing the deficiencies in contemporary anti-spoofing techniques.<n>By innovatively integrating texture analysis and reflective properties associated with genuine human traits, our models distinguish authentic presence from replicas with remarkable precision.
  arXiv  Detail & Related papers  (2025-08-12T17:19:20Z)
• CAST: Cross-Attentive Spatio-Temporal feature fusion for Deepfake detection [0.0]
  CNNs are effective at capturing spatial artifacts, and Transformers excel at modeling temporal inconsistencies.<n>We propose a unified CAST model that leverages cross-attention to effectively fuse spatial and temporal features.<n>We evaluate the performance of our model using the FaceForensics++, Celeb-DF, and DeepfakeDetection datasets.
  arXiv  Detail & Related papers  (2025-06-26T18:51:17Z)
• So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection [75.79507634008631]
  We introduce So-Fake-Set, a social media-oriented dataset with over 2 million high-quality images, diverse generative sources, and imagery synthesized using 35 state-of-the-art generative models.<n>We present So-Fake-R1, an advanced vision-language framework that employs reinforcement learning for highly accurate forgery detection, precise localization, and explainable inference through interpretable visual rationales.
  arXiv  Detail & Related papers  (2025-05-24T11:53:35Z)
• Is Artificial Intelligence Generated Image Detection a Solved Problem? [10.839070838139401]
  AIGIBench is a benchmark designed to rigorously evaluate the robustness and generalization capabilities of state-of-the-art AIGI detectors.<n>It includes 23 diverse fake image subsets that span both advanced and widely adopted image generation techniques.<n>Experiments on 11 advanced detectors demonstrate that, despite their high reported accuracy in controlled settings, these detectors suffer significant performance drops on real-world data.
  arXiv  Detail & Related papers  (2025-05-18T10:00:39Z)
• CapsFake: A Multimodal Capsule Network for Detecting Instruction-Guided Deepfakes [3.2194551406014886]
  deepfake technology threatens the integrity of digital images by enabling subtle, context-aware manipulations.<n>We propose CapsFake, designed to detect such deepfake image edits by integrating low-level capsules from visual, textual, and frequency-domain modalities.<n>High-level capsules, predicted through a competitive routing mechanism, dynamically aggregate local features to identify manipulated regions with precision.
  arXiv  Detail & Related papers  (2025-04-27T12:31:47Z)
• Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection [66.80386429324196]
  We propose a decoupled doubly contrastive adaptation (D$2$CA) approach to learn a purified AU representation.<n>D$2$CA is trained to disentangle AU and domain factors by assessing the quality of synthesized faces.<n>It consistently outperforms state-of-the-art cross-domain AU detection approaches.
  arXiv  Detail & Related papers  (2025-03-12T00:42:17Z)
• Hybrid Deepfake Image Detection: A Comprehensive Dataset-Driven Approach Integrating Convolutional and Attention Mechanisms with Frequency Domain Features [0.6700983301090583]
  We propose an ensemble-based approach that employs three different neural network architectures for deepfake detection.<n>We empirically demonstrate the effectiveness of these models in grouping real and fake images into cohesive clusters.<n>Our weighted ensemble model achieves an excellent accuracy of 93.23% on the validation dataset of the SP Cup 2025 competition.
  arXiv  Detail & Related papers  (2025-02-15T06:02:11Z)
• HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection [4.908389661988192]
  HFMF is a comprehensive two-stage deepfake detection framework.<n>It integrates vision Transformers and convolutional nets through a hierarchical feature fusion mechanism.<n>We demonstrate that our architecture achieves superior performance across diverse dataset benchmarks.
  arXiv  Detail & Related papers  (2025-01-10T00:20:29Z)
• Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models [68.90917438865078]
  Deepfake techniques for facial synthesis and editing pose serious risks for generative models.<n>In this paper, we investigate how detection performance varies across model backbones, types, and datasets.<n>We introduce Contrastive Blur, which enhances performance on facial images, and MINDER, which addresses noise type bias, balancing performance across domains.
  arXiv  Detail & Related papers  (2024-11-28T13:04:45Z)
• StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model [62.25424831998405]
  StealthDiffusion is a framework that modifies AI-generated images into high-quality, imperceptible adversarial examples. It is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries.
  arXiv  Detail & Related papers  (2024-08-11T01:22:29Z)
• DA-HFNet: Progressive Fine-Grained Forgery Image Detection and Localization Based on Dual Attention [12.36906630199689]
  We construct a DA-HFNet forged image dataset guided by text or image-assisted GAN and Diffusion model. Our goal is to utilize a hierarchical progressive network to capture forged artifacts at different scales for detection and localization.
  arXiv  Detail & Related papers  (2024-06-03T16:13:33Z)
• 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)
• PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation [50.556961575275345]
  We propose a perception-aware fusion framework to promote segmentation robustness in adversarial scenes. We show that our scheme substantially enhances the robustness, with gains of 15.3% mIOU, compared with advanced competitors.
  arXiv  Detail & Related papers  (2023-08-08T01:55:44Z)
• MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection [81.59191603867586]
  Sequential deepfake detection aims to identify forged facial regions with the correct sequence for recovery. The recovery of forged images requires knowledge of the manipulation model to implement inverse transformations. We propose Multi-Collaboration and Multi-Supervision Network (MMNet) that handles various spatial scales and sequential permutations in forged face images.
  arXiv  Detail & Related papers  (2023-07-06T02:32:08Z)

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.