TY - GEN
T1 - 2D-FACT
T2 - 2023 IEEE MIT Undergraduate Research Technology Conference, URTC 2023
AU - Ji, Eric
AU - Dong, Boxiang
AU - Samanthula, Bharath
AU - Zhou, Na
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Recent developments in generative artificial intelligence are bringing great concerns for privacy, security and misinformation. Our work focuses on the detection of fake images generated by text-To-image models. We propose a dual-domain CNN-based classifier that utilizes image features in both the spatial and frequency domain. Through an extensive set of experiments, we demonstrate that the frequency domain features facilitate high accuracy, zero-Transfer learning between different generative models, and faster convergence. To our best knowledge, this is the first effective detector against generative models that are finetuned for a specific subject.
AB - Recent developments in generative artificial intelligence are bringing great concerns for privacy, security and misinformation. Our work focuses on the detection of fake images generated by text-To-image models. We propose a dual-domain CNN-based classifier that utilizes image features in both the spatial and frequency domain. Through an extensive set of experiments, we demonstrate that the frequency domain features facilitate high accuracy, zero-Transfer learning between different generative models, and faster convergence. To our best knowledge, this is the first effective detector against generative models that are finetuned for a specific subject.
KW - AI generative model
KW - fake image detection
KW - frequency domain
UR - http://www.scopus.com/inward/record.url?scp=85195465049&partnerID=8YFLogxK
U2 - 10.1109/URTC60662.2023.10535000
DO - 10.1109/URTC60662.2023.10535000
M3 - Conference contribution
AN - SCOPUS:85195465049
T3 - IEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Proceedings
BT - IEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 6 October 2023 through 8 October 2023
ER -