Saved in:
Bibliographic Details
Main Authors: Nguyen, Tuan, Khan, Naseem, Khalil, Issa
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.19212
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915262101454848
author Nguyen, Tuan
Khan, Naseem
Khalil, Issa
author_facet Nguyen, Tuan
Khan, Naseem
Khalil, Issa
contents The rapid evolution of deepfake technology, particularly in instruction-guided image editing, threatens the integrity of digital images by enabling subtle, context-aware manipulations. Generated conditionally from real images and textual prompts, these edits are often imperceptible to both humans and existing detection systems, revealing significant limitations in current defenses. We propose a novel multimodal capsule network, CapsFake, designed to detect such deepfake image edits by integrating low-level capsules from visual, textual, and frequency-domain modalities. High-level capsules, predicted through a competitive routing mechanism, dynamically aggregate local features to identify manipulated regions with precision. Evaluated on diverse datasets, including MagicBrush, Unsplash Edits, Open Images Edits, and Multi-turn Edits, CapsFake outperforms state-of-the-art methods by up to 20% in detection accuracy. Ablation studies validate its robustness, achieving detection rates above 94% under natural perturbations and 96% against adversarial attacks, with excellent generalization to unseen editing scenarios. This approach establishes a powerful framework for countering sophisticated image manipulations.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19212
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CapsFake: A Multimodal Capsule Network for Detecting Instruction-Guided Deepfakes
Nguyen, Tuan
Khan, Naseem
Khalil, Issa
Computer Vision and Pattern Recognition
Artificial Intelligence
The rapid evolution of deepfake technology, particularly in instruction-guided image editing, threatens the integrity of digital images by enabling subtle, context-aware manipulations. Generated conditionally from real images and textual prompts, these edits are often imperceptible to both humans and existing detection systems, revealing significant limitations in current defenses. We propose a novel multimodal capsule network, CapsFake, designed to detect such deepfake image edits by integrating low-level capsules from visual, textual, and frequency-domain modalities. High-level capsules, predicted through a competitive routing mechanism, dynamically aggregate local features to identify manipulated regions with precision. Evaluated on diverse datasets, including MagicBrush, Unsplash Edits, Open Images Edits, and Multi-turn Edits, CapsFake outperforms state-of-the-art methods by up to 20% in detection accuracy. Ablation studies validate its robustness, achieving detection rates above 94% under natural perturbations and 96% against adversarial attacks, with excellent generalization to unseen editing scenarios. This approach establishes a powerful framework for countering sophisticated image manipulations.
title CapsFake: A Multimodal Capsule Network for Detecting Instruction-Guided Deepfakes
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.19212