Publication: Examining performance of idinvert gan model on imitating real human faces
0
0
Issued Date
2023-05-19
Resource Type
Language
eng
File Type
application/pdf
Access Rights
Open Access
Rights
ผลงานนี้เผยแพร่ภายใต้ สัญญาอนุญาตครีเอทีฟคอมมอนส์แบบ แสดงที่มา-ไม่ใช้เพื่อการค้า-ไม่ดัดแปลง 4.0 (CC BY-NC-ND 4.0)
Rights Holder(s)
Srinakharinwirot University
Suggested Citation
Pattanadej Chaengsrisuk, พัฒนเดช แจ้งศรีสุข (2023). Examining performance of idinvert gan model on imitating real human faces. Retrieved from: https://hdl.handle.net/20.500.14740/54203
Alternative Title(s)
การตรวจจับภาพใบหน้าปลอมที่สร้างจากโครงข่ายประสาทเทียมก่อกำเนิดแบบมีคู่ปรปักษ์
Author(s)
Advisor(s)
Organization
Abstract
This study evaluates the performance of IDInvert, a variant of the generative adversarial network (GAN) models, in terms of ability to generate synthetic face images that resemble real ones, while also preserving personal identity. The main focus of the study is to investigate whether current techniques can detect the subtle differences between real and synthetic face images generated by the IDInvert model. The findings reveal that although the IDInvert model produces highly realistic facial images, they do not preserve personal identity, and they can be identified using feature extraction techniques and standard classification models. Overall, the study highlighted the potential risks of using GAN inversion models and emphasized the importance of developing more robust and secure algorithms to prevent the misuse of such technology.
-
-
Degree Name
MASTER OF SCIENCE (M.Sc.)
Degree Level
-
-
-
Degree Discipline
Department Of Computer Science
Degree Grantor(s)
Srinakharinwirot University