PHD CALL

Project #1: Intelligent Multi-Stage and User-centric Ransomware Attack Detection (Advert Ref: SF22/EE/CIS/ISSAC) - https://www.findaphd.com/phds/project/intelligent-multi-stage-and-user-centric-ransomware-attack-detection-advert-ref-sf22-ee-cis-issac/?p144836 (Self-funded)


For UK students, you can apply for a doctoral student loan of up to £27,892. Check here: https://lnkd.in/endHYkme
 

Supervisor: Dr Biju Issac and Co-supervisor: Dr Nauman Aslam

Deadline for applications: Accepting now and start date: 1 October 2022.

 

Ransomware is a type of malicious software designed to deny access to a computer system or data by encrypting it until a ransom is paid. Ransomware uses asymmetric encryption which uses a pair of keys to encrypt and decrypt a file. In 2021, 68.5 percent of businesses were attacked by ransomware, which is an increase from the previous three years and the highest figure reported so far. Half of the total survey respondents each year stated that their employer had been victimized by ransomware. We will investigate and implement an intelligent ransomware attack detection scheme for existing attacks and also for the new variants. The number of ransomware variants has increased rapidly, and the way ransomware works need to be differentiated from malware so as to protect against ransomware‐based attacks. Ransomware generally focuses on file‐related operations in a short burst of time to encrypt files and lock the victim’s computer. The first stage of detection will be based on any matches of the signature with that of known ransomware datasets through optimised machine learning or deep learning approaches. In the second stage, a predictive learning algorithm will be used with conventional metrics and new metrics (Kok et al. 2020) and the predictive model will be trained with data from the application program interface (API) and related features. In the third stage, a heuristic approach that converts log entries into a heterogeneous graph will be done on network log files, to analyse user behaviour with deep learning (Liu et al., 2019). Thus, a multi-stage novel protection mechanism for ransomware detection will be explored and implemented.

Project #2: Intelligent Digital Forensics for Investigating Botnets in IoT-based Attacks (Advert Ref: SF22/EE/CIS/ASLAM) - https://www.findaphd.com/phds/project/intelligent-digital-forensics-for-investigating-botnets-in-iot-based-attacks-advert-ref-sf22-ee-cis-aslam/?p144839 (Self-funded)
 

For UK students, you can apply for a doctoral student loan of up to £27,892. Check here: https://lnkd.in/endHYkme

Supervisor: Dr Nauman Aslam and Co-supervisor: Dr Biju Issac
 

Deadline for applications: Accepting now and start date: 1 October 2022.

With a wide variety of applications, such as home automation, smart grids/cities etc. the IoT systems make compelling targets for cyber-attacks. Network Forensics is the branch of Digital Forensics, where the evidence is network-related and exist in the form of logs, packets and network flows. Popular methods of investigating botnets include Honeypot, Network flow analysis, Intrusion detection systems, Visualization of Network traffic, Deep Packet Analysis etc. Multiple deep learning solutions have been proposed for application in the field of Network Forensics in recent years. Some reported research used stacked auto-encoders in their implementation of a DDoS detection system for software defined networks. The multiple auto-encoders were greedily trained layer-by-layer, with the output of one layer being the input of the next. Then the entire network was fine-tuned as a classifier. Reported accuracy for distinguishing between normal and attack traffic was 99.82%, outperforming other classification methods such as shallow NN, while individual types of DDoS attacks were identified with an accuracy of 95.65%. We will explore using a combination of a one-dimensional CNN and stacked auto-encoders for automatic feature extraction and classification of network traffic, achieving both application identification and traffic characterization in either encrypted or unencrypted traffic. This project will explore the use of Recurrent Neural Network (RNN), Convolutional Neural Networks (CNN), Deep Auto Encoder (DAE), Deep Boltzman Machine (DBM) and Deep Belief Network (DBN), alongside some of the network forensics methods, whereby botnets in IoT can be effectively investigated and mitigated through detection.