← All proceedings

TheIIER INTERNATIONAL CONFERENCE

Proceedings cover: TheIIER INTERNATIONAL CONFERENCE

Istanbul, Turkey 20-01-2023

4 papers

  1. Analysis of Multiple Adversarial Machine Learning Attacks on Convolutional Neural Networks

    Burcum Eken, Seddik M. Djouadi, Selen Ayas

    Paper ID IF-ICCSMLAI-ISTNBL-200123-4331 · Pages 1-5

    Abstract

    With the increase of machine learning applications, cyber-attacks on these applications have also increased in recent years. Even if the machine learning models are used in many fields including transportation and communications, social media, product recommendations, dynamic pricing, and fraud detection, they are still vulnerable to cyber-attacks. Deep neural networks also face a security threat from adversarial examples which are inputs that appear normal but cause an misclassification by the Deep Neural Network. In this paper, first, electric load data from ERCOT is considered as a signal and then converted to an image. After that, we analyze different gradient-based adversarial attacks on a Convolutional Neural Networks (CNN) model designed to classify whether the data from ERCOT belongs to West Station or Far West Station. We also explore robustness of the CNN model to examine the effect of the implemented Adversarial Machine Learning (AML) and finally give an idea for future work in order to design more robust models that could resist adversarial attacks.

    Keywords - Adversarial Machine Learning, Projected Gradient Descent, Convolutional Neural Network.

    Download PDF
  2. A New Payment System Design with Apache Kafka

    Neslihan Yaylicioğlu, Murat Derman

    Paper ID II-ABMITISTA-200123-20468 · Pages 6-8

    Abstract

    Apache Kafka is a highly scalable messaging platform, which provides high throughput with low latency and useful for real-time data processing. This article is about replacing a Messaging Queue technology with Apache Kafka for a Payment system. The legacy Payment system, which was being used for Payment processing and payment distribution to clients, was using a Queue based infrastructure and had various problems due to the limitations of Payment processing rules and increased number of transactions over years. In this article, we present the elucidations offered by Kafka regarding the complications of the legacy system. Moreover, the limitations of the old system with queue messaging technology was discussed in detail.

    Keywords - Payment Distribution, Payment Processing, Apache Kafka, Queue Messaging System

    Download PDF
  3. Achieving the Highest Detection Rate and the Shortest Time in Building Model for Intrusion Detection in Computer Network

    Hadi Najafi Mohsenabad, Mehmet Ali Tut

    Paper ID II-RIETISTA-200123-20827 · Pages 9-14

    Abstract

    Intrusion detection systems (IDS) have developed into a very important research area among computer network security experts as a result of the expanding use of computer networks on the one hand and the rise in the number of attacks on computer networks on the other. In this study, a method utilizing machine learning algorithms is introduced that can detect the detection rate of secure traffic and the detection rate of Brute Force type attacks with 100% accuracy as well as the detection rate of Bot type attacks using the fewest possible identity features with more than 99% accuracy. The training and testing of the proposed methods utilized the CSE-CIC-IDS2018 data set, one of the most recent standard data sets for evaluating the effectiveness of computer network intrusion detection techniques. The CFSS ubset Eval feature selection method has allowed this method to employ less features while maintaining the same level of intrusion detection accuracy. It also takes less time to develop an intrusion detection model than other methods.

    Keywords - Computer Networks, Decision Tree, Feature Selection, Intrusion Detection System.

    Download PDF
  4. Indonesian Government's Roles in Developing Mandarin to Improve Business, Tourism, and Technology Transfer

    Britanugrah Crysanthia Mahadewi, Cheryl Vania Br Situmeang

    Paper ID II-SSEISTA-200123-01 · Pages 15-18

    Abstract

    In the globalization era, which syncs with technology development, China has become one of the developed countries with massive power, peculiarly in the trading industry. This development affects how Mandarin becomes the second international language. As one of the attempts to develop the country, Indonesian government needs to consider the urgency of language education so the communication traffic can be well created. In this study, the authors used a qualitative method with the previous studies and secondary data from the Indonesian government’s database as the reference, particularly Mandarin. Previous policies in the second presidential administration affected the development of Mandarin in Indonesia. It banned Chinese and its whole culture including its language utilization in some periodical time. As a country that is dependent on China in many transactional sectors, Indonesia should escalate its awareness of the use of Mandarin in order to create better communication towards China. So later on, the transaction could be done better for the country's development.

    Keywords - China, Indonesia, Language, Mandarin

    Download PDF