P

py-LMDC (Linux Malware Detection & Classification)

A solution that aims to provide an ML-based approach to increase the security of a system against malicious software like keyloggers, ransomware, & viruses by detecting them before any damage happens.

P

py-LMDC (Linux Malware Detection & Classification)

A solution that aims to provide an ML-based approach to increase the security of a system against malicious software like keyloggers, ransomware, & viruses by detecting them before any damage happens.

The problem py-LMDC (Linux Malware Detection & Classification) solves

Malware is intrusive software designed to damage and destroys computer systems. The common types of malware include computer viruses, computer worms, Ransomware & Keyloggers. This malicious software may destroy crucial data or remove our access from it. Anti-malware is a computer program used to prevent, detect, and remove malware. This anti-malware software help in the detection and thereby prevention of attacks on systems. This project aims to provide an ML-based approach to increase the security of a system against such attacks by detecting the malicious software before any damage.

Challenges we ran into

The challenges we faced are:

The first problem we ran into was handling the highly malicious Malwares for analysis.
We solved this by making the elfs read-only & doing the passive fingerprinting in an isolated virtual environment.

The second was data cleaning and filling in missing values. Elfs' structure varies a lot and, it was tough to find recurrent features to all and find whether a trait was essential for Mal-intentions.
We handled this by testing various feature selection methods to ensure that all relevant ones got selected.

The third was fine-tuning the model's parameters for best results. That involves testing parameter values like the number of trees in a random forest and forest depth.
We solved this by automating this process and saving the best model only.

Discussion