EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving synthetic media generation and detection using generative adversarial networks

Rabbia Zia, Mariam Rehman, Afzaal Hussain, Shahbaz Nazeer, Maria Anjum

PeerJ Computer Science · 20.09.2024 · 10 · e2181

DOI: 10.7717/peerj-cs.2181 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 20.09.2024. Verfasst von Rabbia Zia und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, Government College University Faisalabad, Punjab, Pakistan. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Synthetic images ar­­­e created using computer graphics modeling and artificial intelligence techniques, referred to as deepfakes. They modify human features by using generative models and deep learning algorithms, posing risks violations of social media regulations and spread false information. To address these concerns, the study proposed an improved generative adversarial network (GAN) model which improves accuracy while differentiating between real and fake images focusing on data augmentation and label smoothing strategies for GAN training. The study utilizes a dataset containing human faces and employs DCGAN (deep convolutional generative adversarial network) as the base model. In comparison with the traditional GANs, the proposed GAN outperform in terms of frequently used metrics i.e ., Fréchet Inception Distance (FID) and accuracy. The model effectiveness is demonstrated through evaluation on the Flickr-Faces Nvidia dataset and Fakefaces d­­ataset, achieving an FID score of 55.67, an accuracy of 98.82%, and an F1-score of 0.99 in detection. This study optimizes the model parameters to achieve optimal parameter settings. This study fine-tune the model parameters to reach optimal settings, thereby reducing risks in synthetic image generation. The article introduces an effective framework for both image manipulation and detection.

Schlagwörter

Stichwörter der Autor:innen

Deep neural networksDeepFakeGenerative adversarial networksImage manipulationManipulation detection

Autor:innen und Institutionen

  • Department of Information Technology, Government College University Faisalabad, Punjab, Pakistan.
  • Department of Computer Science, Lahore College for Women University, Lahore, Punjab, Pakistan.

Zitieren

APA

Zia, R., Rehman, M., Hussain, A., Nazeer, S., & Anjum, M. (2024). Improving synthetic media generation and detection using generative adversarial networks. PeerJ Computer Science, 10, e2181. https://doi.org/10.7717/peerj-cs.2181

Vancouver

Zia R, Rehman M, Hussain A, Nazeer S, Anjum M. Improving synthetic media generation and detection using generative adversarial networks. PeerJ Computer Science. 2024;10:e2181. doi:10.7717/peerj-cs.2181

BibTeX
@article{Zia2024,
  author = {Zia, Rabbia and Rehman, Mariam and Hussain, Afzaal and Nazeer, Shahbaz and Anjum, Maria},
  title = {Improving synthetic media generation and detection using generative adversarial networks},
  journal = {PeerJ Computer Science},
  year = {2024},
  volume = {10},
  pages = {e2181},
  doi = {10.7717/peerj-cs.2181}
}
Kostenlos starten →