AI-Generated face detection using multi-feature fusion


Abstract

Deep learning-based image generation techniques have made synthetic face images nearly indistinguishable from real ones. The misuse of these synthetic images can lead to serious issues, including the spread of misinformation, fraud, and identity theft. Therefore, accurate detection of the authenticity of face images is crucial. Most existing studies rely on single feature extraction techniques, making it difficult to effectively detect the increasingly diverse and realistic synthetic face images. To address this challenge, we introduce a novel parallel architecture that fuses multiple feature inputs, combining four feature extraction techniques: raw images, Gray Level Co-occurrence Matrix (GLCM), Edge features, and Local Binary Pattern (LBP). The raw image extracts global features, while GLCM captures texture information, Edge features identify image structures, and LBP extracts local texture features. By combining these complementary features, the parallel architecture analyzes images from multiple dimensions, effectively identifying subtle differences between synthetic and real faces. Furthermore, we compiled a Multidimensional Facial Image Dataset (MFID), containing approximately 92,000 images, considering factors such as the type of generation model, real face quality, and face angle and age, ensuring the dataset's generalization ability. Experimental results demonstrate that our architecture achieves an accuracy of 99.17% and significantly outperforms existing methods on MFID.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.

  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].