This is a very interesting research paper which was according to what I can pick up from multiple Google sources funded by or encouraged by DARPA including a secure site that will not let me access. However it is looking at Deepfake detection methods and areas of research and from my speed read of it and the tables provided CNNRNN (or SCNN as Brainchip calls it) seems to be very good at doing this form of detection. Following is the title, authors and Abstract as well as a paragraph believe it or not which states there are in fact paid trolls are working on the web for businessmen and companies. Who would have thought this possible. So once more I say do not believe anything I or any other anonymous poster puts up to which I now add any one who is not anonymous until you have independently confirmed what they are stating :Deepfakes Generation and Detection: State-of-the-art,open challenges, countermeasures, and way forward
Momina Masood1 , Mariam Nawaz2 , Khalid Mahmood Malik3 , Ali Javed4 , Aun Irtaza5 1,2Department of Computer Science, University of Engineering and Technology-Taxila, Pakistan 3,4Department of Computer Science and Engineering, Oakland University, Rochester, MI, USA 5 Electrical and Computer Engineering Department, University of Michigan-Dearborn, MI, USA
Abstract
Easy access to audio-visual content on social media, combined with the availability of modern tools such as Tensorflow or Keras, open-source trained models, and economical computing infrastructure, and the rapid evolution of deep-learning (DL) methods, especially Generative Adversarial Networks (GAN), have made it possible to generate deepfakes to disseminate disinformation, revenge porn, financial frauds, hoaxes, and to disrupt government functioning. The existing surveys have mainly focused on deepfake video detection only. No attempt has been made to review approaches for detection and generation of both audio and video deepfakes. This paper provides a comprehensive review and detailed analysis of existing tools and machine learning (ML) based approaches for deepfake generation and the methodologies used to detect such manipulations for the detection and generation of both audio and video deepfakes. For each category of deepfake, we discuss information related to manipulation approaches, current public datasets, and key standards for the performance evaluation of deepfake detection techniques along with their results. Additionally, we also discuss open challenges and enumerate future directions to guide future researchers on issues that need to be considered to improve the domains of both the deepfake generation and detection. This work is expected to assist the readers in understanding the creation and detection mechanisms of deepfake, along with their current limitations and future direction….
Trolls: Independent Trolls are hobbyists who spread inflammatory information to cause disorder and reactions in society by playing with the emotions of people [18]. For example, posting audio-visual manipulated racist or sexist content and infuriating individuals may promote hatred among the individuals. Similarly, during the 2020 election campaign of US President Donald Trump, conflicting narratives about Trump and Biden were circulated on social media, contributing to an environment of fear [19]. Opposed to independent trolls who spread false information for their own satisfaction, hired trolls will perform the same job for monetary benefits. Different actors, like political parties, businessmen, and companies routinely hire people to forge news related to their competitors and spread it in the market [20]. For example, according to a report published by Western intelligence [21], Russia is running “troll farms,” where trolls are trained to affect conversations related to national or international issues. According to these reports, deepfake videos generated by hired trolls are the newest weapon in the ongoing fabricated news war that can bring a more devastating effect on society
https://static1.squarespace.com/static/5fc283fb2bbd74065810d034/t/5fc557e89ee0f32b870592b8/1606768616092/host_based_intrusion_detection_system_with_combined_cnn_rnn_model.pdf
MY OPINION ONLY DYOR
FF.
AKIDA Ballista
- Forums
- ASX - By Stock
- 2021 BRN Discussion
This is a very interesting research paper which was according to...
-
-
- There are more pages in this discussion • 28,607 more messages in this thread...
You’re viewing a single post only. To view the entire thread just sign in or Join Now (FREE)
Featured News
Add BRN (ASX) to my watchlist
|
|||||
Last
15.5¢ |
Change
0.000(0.00%) |
Mkt cap ! $304.1M |
Open | High | Low | Value | Volume |
15.5¢ | 16.0¢ | 15.5¢ | $380.9K | 2.450M |
Buyers (Bids)
No. | Vol. | Price($) |
---|---|---|
36 | 1104665 | 15.5¢ |
Sellers (Offers)
Price($) | Vol. | No. |
---|---|---|
16.0¢ | 478969 | 12 |
View Market Depth
No. | Vol. | Price($) |
---|---|---|
36 | 1104665 | 0.155 |
132 | 4542755 | 0.150 |
39 | 916706 | 0.145 |
40 | 995029 | 0.140 |
7 | 226494 | 0.135 |
Price($) | Vol. | No. |
---|---|---|
0.160 | 478969 | 12 |
0.165 | 867511 | 15 |
0.170 | 953694 | 17 |
0.175 | 887112 | 13 |
0.180 | 1345875 | 18 |
Last trade - 16.10pm 06/09/2024 (20 minute delay) ? |
Featured News
BRN (ASX) Chart |