View Proposal

---

Proposer

Oleksandr Letychevskyi

Title

AI methods in detecting intrusions into software systems.

Goal

Create a neuron system for attack detecting and prevention

Description

Create a neural network that classifies cyberattacks based on existing datasets. Create a program (wrapper) that works as a firewall for a software system to detect and prevent intrusions, using the created neural network. Estimate accuracy and adversarial attack resistance. Consider the problem of verification of the neuron network.

Resources

Background

Url

Difficulty Level

Moderate

Ethical Approval

None

Number Of Students

2

Supervisor

Oleksandr Letychevskyi

Keywords

cybersecurity, ai methods, adversarial attacks

Degrees