Nidaa Flaih Hassan
University of Technology

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Indonesian Journal of Electrical Engineering and Computer Science

Video mosaic watermarking using plasma key Nidaa Flaih Hassan; Akbas Ezaldeen Ali; Teaba Wala Aldeen; Ayad Al-Adhami
Indonesian Journal of Electrical Engineering and Computer Science Vol 22, No 2: May 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v22.i2.pp619-628

Abstract

Video watermarking is one of the most widespread techniques amongst the many watermarking techniques presently are used; this is because the extreme existences of copyright abuse and misappropriation occur for video content. In this paper, a new watermarking algorithm is proposed to embed logo in digital video for copyright protection. To make the watermarks more robust to attack, host frame and host embedding indices must be changeable. A new algorithm is proposed to determined host frames by plasma function, Host location indices in frames are also determined by another plasma function. Logo is divided using the mosaic principle, the size of mosaic blocks is determined initially according to the degree of protection, whenever the size of mosaic blocks is small, it leads to safe embedding, and vice versa. Digital watermarks are embedded easily without any degradation for video quality, In the other side, the watermarked is retrieved by applying the reverse of proposed embedding algorithm and extracted watermark is still recognizable. The experimental results confirm that watermark is robust against three types of attacks which are addition of Gaussian noise, JPEG compression, and rotation process.
Performance analysis of flow-based attacks detection on CSE-CIC-IDS2018 dataset using deep learning Rawaa Ismael Farhan; Abeer Tariq Maolood; Nidaa Flaih Hassan
Indonesian Journal of Electrical Engineering and Computer Science Vol 20, No 3: December 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v20.i3.pp1413-1418

Abstract

The emergence of the internet of things (IOT) as a result of the development of the communications system has made the study of cyber security more important. Day after day, attacks evolve and new attacks are emerged. Hence, network anomaly-based intrusion detection system is become very important, which plays an important role in protecting the network through early detection of attacks. Because of the development in  machine learning and the emergence of deep learning field,  and its ability to extract high-level features with high accuracy, these systems have been included to work with real network traffic CSE-CIC-IDS2018 for a wide range of intrusions and normal behavior as an ideal method of testing and evaluation. In this paper, we test and evaluate our deep model (DNN) which has achieved a good detection accuracy of about 90%.