[2022-09-30] Prof. Jiann-Liang Chen,NTUST,"DeepFake-雙重注意力神經網路技術於人臉偽造影片檢測"

Poster:HSIN-YI SUNGPost date:2022-09-05
 Title:  DeepFake-雙重注意力神經網路技術於人臉偽造影片檢測

Date: 2022-09-30 2:20 -3:10 pm
Location: R103

Speaker: 陳俊良教授,臺灣科技大學電機資訊學院院長

Hosted by: Prof. Phone Lin


Forged videos are commonly spread online. Most have malicious content and cause serious information security problems. The most critical issue in deepfake detection is the identification of traces of tampering in fake videos. This talk introduces a Dual Attention Forgery Detection Network (DAFDN), which embeds a spatial reduction attention block (SRAB) and a forgery feature attention module (FFAM) to the backbone network. DAFDN embeds the two proposed attention mechanisms and enables the convolution neural network to extract peculiar traces left by images’ warping. This study uses two benchmark datasets, DFDC and FaceForensics++, to compare the performance of the proposed DAFDN with other methods. The results show that the proposed DAFDN mechanism achieves AUC scores of 0.911 and 0.945 in the datasets DFDC and FaceForensics++, respectively. These results are better than those of previously developed methods, such as XceptionNet and EfficientNet-related methods.


電資學院院長 (2021.02-迄今 )/電機系系主任 (2015.08-2018.07)
電機系特聘教授(2013.08-迄今 )


資訊工程學門召集人 (2022.01 迄今 )
行政院科技政策諮詢專家室諮詢專家/資深顧問 (2019-2021)
東華大學資工系主任理工學院 副院長 (1997~2009)
台灣大學電機系 博士 (1987~1989)
Last modification time:2022-09-05 PM 6:10

cron web_use_log