Technical Workshop : (Hands-On) Demystifying Neural Networks And Building Cybersecurity Applications
[Book My Seat]

Trainer: Arnab Chattopadhyay

Arnab Chattopadhyay (VP Engineering at Firecompass; past technical architect at Business Telecom)

Creator of Bad Llama, How to Turn Good Llama into a Toxic Llama | CTO & Co-Founder of FireCompass

Arnab’s expertise lie in providing solutions to complex problems in the area of IT Security. He has 23+ years of experience in leadership roles at large organisations like British Telecom, Tech Mahindra, iViZ (part of Synopsys), Metric Stream, Capgemini, IBM & more. Arnab was one of the key members to have worked in the BT21CN, one of the largest transformation project in the telecom world aimed at complete transformation of BT’s telecom network to Next Generation Network (NGN).

>>Block My Seat For Workshop Session 

Workshop Summary : 

Workshop Duration: 4 Hours, 1/2 Day
Date: 30th May, Thursday, 2024

Description:

This workshop is designed for a security technical audience including Appsec Pentesters, Security Engineers, Security Architects, and AI/ML practitioners, Software Developers who have started
exploring Neural Networks or need it for their profession.

Workshop Agenda:

1. Part 1: Introduction to Neural Networks

• a. Mathematical Basics for Neural Networks
  Introduction to linear algebra and calculus concepts
  Vector and matrix operations
• b. Neural Network Basics
  Mathematical representation of a single neuron
  Building a simple neural network with mathematical notation
• c. Activation Functions and Their Mathematics
  Exploring mathematical functions (Sigmoid, ReLU) used in activation functions
  Impact of activation functions on neural network behavior
• d. Hands-On Exercise: Implementing a Single Neuron
  Using Python and a library (e.g., NumPy) to implement a single neuron mathematically

2. Part 2: Deep Dive into Neural Networks

• a. Multilayer Perceptrons (MLPs) and Backpropagation
  Mathematical structure of MLPs
  Backpropagation algorithm and its mathematical foundation
• b. Optimization Algorithms with Mathematics
  Understanding gradient descent and its variants
  Updating weights using derivatives and gradients
• c. Loss Functions and Minimization
  Mathematical representation of common loss functions
  Minimizing loss for training neural networks
• d. Hands-On Exercise: Training a Neural Network for Cybersecurity
  Implementing a simple neural network for binary classification (e.g., detecting malicious activity)

3. Part 3 : Cybersecurity Applications and Advanced Topics

• a. Introduction to Cybersecurity in Neural Networks
  Overview of how neural networks are used in cybersecurity
  Examples of applications (e.g., intrusion detection)
• b. Advanced Neural Network Architectures
  Introduction to convolutional neural networks (CNNs) and their mathematical structure
  Brief overview of recurrent neural networks (RNNs)
• c. Hands-On Project: Building a Cybersecurity Model
  Participants work on a project to implement a neural network for cybersecurity using a provided dataset

4. Part 4 : Closing Session: Challenges, Next Steps, and Q&A

• a. Challenges in Neural Networks for Cybersecurity
  Dealing with imbalanced datasets
  Considerations for real-world deployment
• b. Next Steps and Resources for Further Learning
  Recommendations for additional study and practical applications
  Cybersecurity resources and communities
• c. Closing Remarks and Q&A
  Addressing participant questions and providing additional guidance

>>Block My Seat For Workshop Session  

Candidate Requirements:

• The course is beginner friendly
• Some basic coding experience will help

You need to bring:

Hardware: 

• A laptop with internet access

Who Should Attend ? 

• This workshop is designed for a technical audience including Appsec Pentesters, Security Engineers, Security Architects, and AI/ML practitioners, Software Developers who have started
  exploring Neural Networks or need it for their profession.

Set Expectations:

• Hands on

>>Block My Seat For Workshop Session