DeepFake Detection 深偽偵測

Welcome

Discover the truth behind your videos and images with our cutting-edge detection model. Identifying fake content generated by AI. Powered by advanced recognition technology and supported by Taiwan's NSTC and the NCHC, we set the standard for multimedia verification.

探究您的視頻與圖片是否為真，我們領先的偵測模型能夠辨識出由AI產生的偽造內容。專精於偵測臉部置換、操弄以及生成的虛假影像，憑藉先進辨識技術，並獲台國科會及國家高效能運算中心(NCHC)支持，我們為多媒體真實性鑑定設立了新標準。

MAIN FUNCTION 主功能

Upload an image/video to verify its authenticity. Note: This tool is for academic use only.

請上傳影像/視頻以核實其真實性。註：本項目僅限學術用途。

Step 1: Choose an Image / Video

Only accept 'png', 'jpg', 'mp4', 'mov' file extension, and file size should be under 50MB.

DETECTION RESULT 偵測結果

CITATIONS

If you find our website useful, you could cite our paper in a BibTeX form below:

@inproceedings{zhuang2019detecting, title={Detecting generated image based on a coupled network with two-step pairwise learning}, author={Zhuang, Yi-Xiu and Hsu, Chih-Chung}, booktitle={2019 IEEE International Conference on Image Processing (ICIP)}, pages={3212--3216}, year={2019}, organization={IEEE}}

@ARTICLE{10061274, author={Chen, Guan-Lin and Hsu, Chih-Chung}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, title={Jointly Defending DeepFake Manipulation and Adversarial Attack using Decoy Mechanism}, year={2023}, volume={}, number={}, pages={1-11}, doi={10.1109/TPAMI.2023.3253390}}

@Article{app10010370, AUTHOR = {Hsu, Chih-Chung and Zhuang, Yi-Xiu and Lee, Chia-Yen}, TITLE = {Deep Fake Image Detection Based on Pairwise Learning}, JOURNAL = {Applied Sciences}, VOLUME = {10}, YEAR = {2020}, NUMBER = {1}, ARTICLE-NUMBER = {370}, URL = {https://www.mdpi.com/2076-3417/10/1/370}, ISSN = {2076-3417}, DOI = {10.3390/app10010370}}