- Blog
- CV generator
- Community
- Documentation
Bamidele Popoola
Chief Technology Officer at Code_Secure
Nuneaton, United Kingdom
I am a versatile tech professional, with experience across Networking, Blue and Red Team Cyber Security, DevOps and Python programming. A huge fan of open source software and decentralisation space, as I believe that technology can be the catalyst for positive change in the world, and these spaces are focused on democratising technology.
CodersRank Score
What is this?
This represents your current experience. It calculates by analyzing your connected repositories. By measuring your skills by your code, we are creating the ranking, so you can know how good are you comparing to another developers and what you have to improve to be better
Information on how to increase score and ranking details you can find in this blog post.
461.8
CodersRank Rank
Top 2%
Top 100
Jupyter Notebook
Developer
United Kingdom
Top 50
Python
Developer
United Kingdom
Top 5
Scikit-Learn
Developer
United Kingdom
Highest experience points: 0 points,
0 activities in the last year
Python
387.5
exp.
Shell
29.5
exp.
HTML
16.8
exp.
Jupyter Notebook
15.4
exp.
List your work history, including any contracts or internships
Code_Secure
Mar 2023 - Present (1 year 11 months)
Chief Technology Officer
Birthed as a research project within Vergroot Development Ltd and in collaboration with Birmingham City University, Code Secure seeks to provide technical control against the issue of IP theft plaguing the outsourcing industry.
As CTO of Code Secure, I have been leading the development of cutting-edge technology solutions to address the critical security challenges facing businesses today. My focus has been on leveraging the latest advances in homomorphic encryption, blockchain, and containerization technologies to create a secure collaboration environment that enables contractors to perform their tasks efficiently while providing companies with granular control over access to code and data.
My technical expertise has been instrumental in the AGILE testing and deployment and redeployment of Code Secure's Searchable Encryption and Verifiable Automation features. I have also overseen the creation of Secure Execution Environments and AI-enabled testing and validation tools to ensure that the platform meets the highest security and functionality standards.
With my deep understanding of emerging technologies and proven track record in driving innovative technologies to the forefront of active development, Code Secure will define a new market: Secure Outsourcing Solutions, and continue to be at the forefront in the years ahead.
As CTO of Code Secure, I have been leading the development of cutting-edge technology solutions to address the critical security challenges facing businesses today. My focus has been on leveraging the latest advances in homomorphic encryption, blockchain, and containerization technologies to create a secure collaboration environment that enables contractors to perform their tasks efficiently while providing companies with granular control over access to code and data.
My technical expertise has been instrumental in the AGILE testing and deployment and redeployment of Code Secure's Searchable Encryption and Verifiable Automation features. I have also overseen the creation of Secure Execution Environments and AI-enabled testing and validation tools to ensure that the platform meets the highest security and functionality standards.
With my deep understanding of emerging technologies and proven track record in driving innovative technologies to the forefront of active development, Code Secure will define a new market: Secure Outsourcing Solutions, and continue to be at the forefront in the years ahead.
Vergroot Development
Jan 2023 - Present (2 years 1 month)
Chief Executive Officer
INCO
Apr 2022 - Mar 2023 (11 months)
IT Trainer
Roles and Responsibilities included:
Delivered comprehensive training sessions on various IT support topics for individuals seeking Google IT Support Certification
Utilized Zoom for virtual delivery of training sessions to participants in different locations
Developed and implemented lesson plans, training materials, and assessments to ensure thorough understanding of course content
Led hands-on exercises and interactive discussions to promote engagement and participation
Provided individualized support and feedback to participants to address specific needs and improve understanding
Monitored and evaluated participants' progress throughout the training program to ensure successful completion
Assisted participants with the Google IT Support Certification exam preparation and provided guidance on best practices for passing the exam.
Delivered comprehensive training sessions on various IT support topics for individuals seeking Google IT Support Certification
Utilized Zoom for virtual delivery of training sessions to participants in different locations
Developed and implemented lesson plans, training materials, and assessments to ensure thorough understanding of course content
Led hands-on exercises and interactive discussions to promote engagement and participation
Provided individualized support and feedback to participants to address specific needs and improve understanding
Monitored and evaluated participants' progress throughout the training program to ensure successful completion
Assisted participants with the Google IT Support Certification exam preparation and provided guidance on best practices for passing the exam.
Add some compelling projects here to demonstrate your experience
DEDaLoRDD (Decomposition Enhanced Decision Trees applied to Low-Rate DOS Detection )
Oct 2020 - May 2021
Low-Rate Denial of Service (LDOS) attacks are difficult to identify because of their cautious
nature. A couple of proposals have been made towards LDOS detection, however just a limited
handful, have presented a case for the use of AI strategies towards detection.
This paper presents a novel ensemble algorithm, decomposing target classes employing the k-Means clustering
algorithm, with the aim of boosting class diversity, and reducing model overfitting. This algorithm is termed Random Class Decomposition (RADE).
With each individual model trained with a random number of sub-classes, each tree acquires an alternate point of view. Employing a Decision Tree Classifier, this is surveyed against the two fundamental ensemble methods – bagging (Random Forest) and boosting (XGBoost).
The results present RADE as a first-class option for working with large datasets (10,000+ instances).
Finally, applying the (Sharafaldin et al., 2018) CIC-IDS 2017 imbalanced dataset, a modified
RADE algorithm with the K-Nearest Neighours (k-NN) classifier will be assessed against (Pérez-Díaz et al., 2020) results applying various machine and deep learning algorithms, with the aim of introducing a substitute way to deal with LDOS detection.
The results depict the need for
supplementary exploration into imbalanced classification methods before a finalised
DEDaLoRDD model can be constructed.
nature. A couple of proposals have been made towards LDOS detection, however just a limited
handful, have presented a case for the use of AI strategies towards detection.
This paper presents a novel ensemble algorithm, decomposing target classes employing the k-Means clustering
algorithm, with the aim of boosting class diversity, and reducing model overfitting. This algorithm is termed Random Class Decomposition (RADE).
With each individual model trained with a random number of sub-classes, each tree acquires an alternate point of view. Employing a Decision Tree Classifier, this is surveyed against the two fundamental ensemble methods – bagging (Random Forest) and boosting (XGBoost).
The results present RADE as a first-class option for working with large datasets (10,000+ instances).
Finally, applying the (Sharafaldin et al., 2018) CIC-IDS 2017 imbalanced dataset, a modified
RADE algorithm with the K-Nearest Neighours (k-NN) classifier will be assessed against (Pérez-Díaz et al., 2020) results applying various machine and deep learning algorithms, with the aim of introducing a substitute way to deal with LDOS detection.
The results depict the need for
supplementary exploration into imbalanced classification methods before a finalised
DEDaLoRDD model can be constructed.
RADE (Random Class Decomposition Patterns for Ensemble Learning)
Nov 2019 - Present
This project presents a new method of machine learning classification applying class decomposition and ensemble learning. The algorithm trains each model in the ensemble with data that has each class broken down into a random number of sub-classes.
The intended result is by randomising the number of sub-classes, model over-fitting is reduced. Also, by having each model trained with a random number of sub-classes each tree gain a different perspective on the data, thus reducing bias towards one class.
To test this new method, experiments are carried out against XGBoost and RandomForest models, keeping the amount of estimators equal.
The performance of the algorithms are measured utilising the accuracy, f1-measure, and AUC metrics, over 50, 100, 500, and 1000 estimators. Data containing different amounts of targets, attributes and instances are applied to testing to paint a complete picture of algorithm performance.
The intended result is by randomising the number of sub-classes, model over-fitting is reduced. Also, by having each model trained with a random number of sub-classes each tree gain a different perspective on the data, thus reducing bias towards one class.
To test this new method, experiments are carried out against XGBoost and RandomForest models, keeping the amount of estimators equal.
The performance of the algorithms are measured utilising the accuracy, f1-measure, and AUC metrics, over 50, 100, 500, and 1000 estimators. Data containing different amounts of targets, attributes and instances are applied to testing to paint a complete picture of algorithm performance.
Oracle Dragons Den
Jul 2018 - Sep 2018
Education Data Science Explorer - a tool to help move STEAM subject into the digital age, customisable to all ages and learning abilities, by offering a platform of industry standard tools to learners from KS3 to Postgraduate levels.
This section lets you add any degrees or diplomas you have earned.
Birmingham City University
MSc, Cyber Security
Jul 2021 - Present
Birmingham City University
BSc, Computer Networks and Security
Jul 2017 - Jul 2021
Grade: 1st Class Honours
Metropolia University of Applied Sciences
Erasmus Exchange Study Abroad, Information Technology
Jan 2019 - Jun 2020
Microsoft
Microsoft Certified: Azure Fundamentals
Jul 2021
LinkedIn
Learning Python Generators
Jan 2020
Microsoft
MTA: Mobility and Device Fundamentals - Certified 2019
Dec 2019