The escalating incidence of internal attacks across computer networks has raised significant concerns among service providers. Safeguarding a computer network against malicious activities, such as unauthorized user access, including from insiders, necessitates the implementation of precise intrusion detection systems.
The objective of intrusion detection learning is to develop a predictive or categorical model with the capability to differentiate between attacks and normal connections. These network attacks can be broadly categorized into four major types:
- DOS/DDOS (Denial of Service/ Distributed Denial of Service Attacks)
- Probing
- U2R (User to Root privelege escalation)
- R2L (Remote to Local intruder logins)
We hypothesize that traditional machine learning algorithms will not suffice and there exists a need for a sequential neural network architecture to achieve full classification potential.
The detailed Project Report can be found here.
 |
 |
 |
 |
|
|---|---|---|---|---|
| Abhijna Raghavendra | Anjali | Mansi Gupta | Disha Chetan Patil | Swati Singh |