Cyber Security 19ECSE401
Course Projects
2022 - 23
Possible Problem Areas:
(Students shall read these papers and propose small improvement (looking at scope for future work)
to enhance the performance of exiting solution. However, students shall select other papers too but
of similar complexity)

Generating Network Intrusion Detection Dataset Based on Real and Encrypted
Synthetic Attack Traffic

Fast, Lean, and Accurate: Modeling Password Guessability Using Neural
Networks

Outside the Closed World: On Using Machine Learning for Network Intrusion
Detection

Anomalous Payload-Based Network Intrusion Detection

Malicious PDF detection using metadata and structural features

Adversarial support vector machine learning

Exploiting machine learning to subvert your spam filter

CAMP – Content Agnostic Malware Protection

Notos – Building a Dynamic Reputation System for DNS

Kopis – Detecting malware domains at the upper dns hierarchy

Pleiades – From Throw-away Traffic To Bots – Detecting The Rise Of DGAbased Malware

EXPOSURE – Finding Malicious Domains Using Passive DNS Analysis

Polonium – Tera-Scale Graph Mining for Malware Detection

Nazca – Detecting Malware Distribution in Large-Scale Networks

PAYL – Anomalous Payload-based Network Intrusion Detection

Anagram – A Content Anomaly Detector Resistant to Mimicry Attacks

Applications of Machine Learning in Cyber Security

Dimension Reduction in Network Attacks Detection Systems

Rise of the machines: Machine Learning & its cyber security applications

Machine Learning in Cyber Security: Age of the Centaurs

Automatically Evading Classifiers A Case Study on PDF Malware Classifiers

Weaponizing Data Science for Social Engineering — Automated E2E Spear
Phishing on Twitter

Machine Learning: A Threat-Hunting Reality Check

Neural Network-based Graph Embedding for Cross-Platform Binary Code
Similarity Detection

Practical Secure Aggregation for Privacy-Preserving Machine Learning

DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep
Learning

eXpose: A Character-Level Convolutional Neural Network with Embeddings
For Detecting Malicious URLs, File Paths and Registry Keys

Big Data Technologies for Security Event Correlation Based on Event Type
Accounting (RUS)

Investigation of The Use of Neural Networks for Detecting Low-Intensive
Ddоs-Atak of Applied Level (RUS)

Detecting Malicious PowerShell Commands using Deep Neural Networks

Machine Learning DDoS Detection for Consumer Internet of Things Devices

Anomaly Detection in Computer System by Intellectual Analysis of System
Journals (RUS)

EMBER: An Open Dataset for Training Static PE Malware Machine Learning
Models

A state-of-the-art survey of malware detection approaches using data mining
techniques.

Investigation of malicious portable executable file detection on network using
supervised learning techniques.

Machine Learning in Cybersecurity: A Guide

Outside the Closed World: On Using Machine Learning For Network Intrusion
Detection

Machine Learning Based Network Vulnerability Analysis of Industrial Internet
of Things

Hopper: Modeling and Detecting Lateral Movement

Finding Effective Security Strategies through Reinforcement Learning and SelfPlay

Intrusion Prevention through Optimal Stopping