20TL045_IDS for Cyber Security AI,ML Based (1).pptx

FYP PROJECT

1. Intrusion Detection System Enhancing Cyber Security Through AI and ML-Based DEPARTMENT OF TELECOMMUNICATION, MUET BATCH 20TL

2. FYP Presentation DEPARTMENT OF TELECOMMUNICATION, MUET BATCH 20TL Naimtaullah (member) 20TL018 Zahid Ab Kunbhar (GL) 20TL045 Mirza Sufiyan(member) 20-19TL79 Dr Aftab Ahmed Memon (Supervisor) Sir Talha Qaimkhani (Co-supervisor)

3. Problem Statement Background and Motivation Literature Review Aim and Objectives Methodology Timeline Social Impacts References CONTENTS DEPARTMENT OF TELECOMMUNICATION, MUET BATCH 20TL

4. PROBLEM STATEMENT Traditional cyber-security struggles against evolving cyber threats. This project deploys AI and ML for a dynamic, preemptive approach, setting new benchmarks for rapid threat response. 01 DEPARTMENT OF TELECOMMUNICATION, MUET BATCH 20TL

5. BACKGROUND & MOTIVATION In the current tech era, global cybercrime escalation calls for proactive measures. Committed to addressing this surge our focus is on leveraging cutting-edge technologies Artificial Intelligence (AI) and Machine Learning (ML). By harnessing AI and ML algorithms, we aim to fortify defenses against cyber threats, developing advanced systems to counteract attacks and set a benchmark for enhanced cyber-security in this dynamic landscape. 02 DEPARTMENT OF TELECOMMUNICATION, MUET BATCH 20TL

6. 03 LITERATURE REVIIEW REF TITLE SUMMARY REMARKS 01 Intrusion Detection Systems using Supervised Machine Learning Techniques: A survey In this paper the Detecting unique attacks, especially anomalies, poses a significant challenge. Our study highlights the pivotal role of Intrusion Detection Systems (IDS) and supervised learning algorithms in countering cyber threats, emphasizing optimal performance for effective anomaly detection. 02 Survey of intrusion detection systems: techniques, datasets and challenges The paper provides a current taxonomy, reviews IDS research, and classifies proposed systems. It outlines existing IDSs, surveys data-mining techniques, and explores signature-based and anomaly-based methods. Challenges in building IDS, varying effectiveness of data mining techniques, and critical evaluation factors like time are discussed, highlighting gaps in existing research. 03 Enhancement of Intrusion Detection System using Machine Learning This research explores the surge in network attacks in the digital age. Utilizing Intrusion Detection Systems (IDS), as depicted enhance security by closely monitoring firewall and router functions. The research delves into the rising challenges of digital-era network attacks. Utilizing IDS and machine learning it bolsters cyber security by enhancing threat detection precision, minimizing false alarms. DEPARTMENT OF TELECOMMUNICATION, MUET BATCH 20TL

7. 04 AIMS AND OBJECTIVES AIM OF THE PROJECT Develop an Intrusion Detection System (IDS) leveraging AI and ML for enhanced cyber security. Achieve real-time identification, minimizing false positives/negatives. OBJECTIVES Implement an autonomous response system for threat mitigation. Achieve precise threat detection through optimized feature extraction. Ensure real-time responsiveness to counter evolving threats promptly. Evaluate IDS with emphasis on accuracy and minimal false positives. Contribute to cyber security knowledge by addressing limitations and suggesting future research for enhanced intrusion detection source use, and provide comprehensive documentation. DEPARTMENT OF TELECOMMUNICATION, MUET BATCH 20TL

8. 05 TOOLS AND SOCIAL IMPACTS: TOOLS Python for AI/ML development TensorFlow , Pandas , Keras , Wireshark , Jupyter Notebooks , Docker , Seaborn , HashLib , SQLite we will utilize these tools for our project implementations SOCIAL IMPACTS (SDG’s) Industry, Innovation, and Infrastructure Peace, Justice, and Strong Institutions Quality Education Decent Work and Economic Growth DEPARTMENT OF TELECOMMUNICATION, MUET BATCH 20TL

9. 06 TIMELINE DEPARTMENT OF TELECOMMUNICATION, MUET BATCH 20TL Working on PPT 07/12/2023 15/12 /2023 12/04/2023 1 0/01/2024 22/01 /2023 Get Familiar With Tools Literature Review Finalize the PPT work Getting the stuff

10. 07 REFRENCES: 1. Khraisat et al. Cybersecurity (2019) 2:20 Survey of intrusion detection systems: techniques, datasets and challenges Ansam Khraisat* , Iqbal Gondal, Peter Vamplew and Joarder Kamruzzaman. A Study of Network Intrusion Detection Systems Using Artificial Intelligence/Machine Learning P.; Newe, T.; Dhirani, L.L.; O’Connell, E.; O’Shea, D.; Lee, B.; Rao, M. A Study of Network Intrusion Detection Systems Using Artificial Intelligence/Machine Learning. Appl. Sci. 2022, 12, 11752. 3 . A comprehensive review of AI based intrusion detection system Sowmya T.a,* , Mary Anita E.A.b d 30 October 2022

11. 08 REFRENCES: 4. The 13th International Conference on Ambient Systems, Networks and Technologies (ANT) March 22-25, 2022, Porto, Portugal Intrusion Detection Systems using Supervised Machine Learning Techniques: A survey Emad E. Abdallah*, Wafa’ Eleisah, Ahmed Fawzi Otoom 5. Hammad, M., El-medany , W., & Ismail, Y. (2020, December). Intrusion Detection System using Feature Selection With Clustering and Classification Machine Learning Algorithms on the UNSW-NB15 dataset. In 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies (3ICT) (pp. 1-6). IEEE

12. Any Query you may ask. THANK YOU!