Detecting Deepfakes under Anti-forensics Attacks
| dc.contributor.author | Liu, Qingzhong | |
| dc.contributor.author | Celebi, Naciye | |
| dc.contributor.author | Zhou, Bing | |
| dc.date.accessioned | 2023-11-20T22:32:50Z | |
| dc.date.available | 2023-11-20T22:32:50Z | |
| dc.date.issued | 2023-10-15 | |
| dc.description.abstract | While AI is vastly evolving, wherein deepfake techniques may be used to generate more realistic faces, voices, and videos, many deepfake-based fraudulent cases are increasingly occurring. To combat deepfake-based forgery, several methods have been proposed wherein the most astonishing methods are based on convolution neural network (CNN). However, most intelligent detection systems are underrepresenting in exposing the deepfake images under anti-forensics attacks, e.g., rescaling the image, inserting noises, and compressing the image again. To our knowledge, it still falls short of an intelligent detection system being able to detect deepfake and other advanced image forgery together. Additionally, it falls short of a comprehensive comparison study on the latest deep learning models for the deepfake detection. In this study, we apply the latest deep learning models for deepfake detection under pos anti-forensics processing mixed with seam-carving and copy-move forgery images in JPEG. Our study shows that different deep learning models have different distinction capability. Experimental results show that some latest deep learning models are effective in detecting deepfake images under post anti-forensics processing in JPEG images, they are also performing well in detecting seam-carving and copy-move forgery. Our study also shows that it is relatively easy to detect deepfake compared to the detection of seam carving forgery detection under antiforensics processing in JPEG images. | |
| dc.identifier.citation | Liu, Q., Celebi, N., Zhou, B., Chen, Z. (2023) Detecting Deepfakes under Anti-forensics Processing Mixed with Seam Carving and Copy-move Forgery in JPEG Images by Using SOTA Deep Learning Models. (Report No. IHS/CR-2023-1003). The Sam Houston State University Institute for Homeland Security. https://doi.org/10.17605/OSF.IO/82UTW | |
| dc.identifier.uri | https://hdl.handle.net/20.500.11875/4259 | |
| dc.language.iso | en_US | |
| dc.publisher | Institute for Homeland Security | |
| dc.relation.ispartofseries | IHS; CR-2023-1003 | |
| dc.subject | Deepfake | |
| dc.subject | adversarial | |
| dc.subject | anti-forensics | |
| dc.subject | seamcarving | |
| dc.subject | copy-move | |
| dc.subject | image forgery | |
| dc.subject | deep learning | |
| dc.subject | JPEG | |
| dc.title | Detecting Deepfakes under Anti-forensics Attacks | |
| dc.type | Article |