Distributed Ledger Technology-based Vulnerability Database Using Machine Learning Methods

There exists many vulnerability databases but these databases are generally centralized which arises a huge controversy with being a secure database because centralized databases contain some security problems such as SQL injection attacks. This problem led me to think a different vulnerability database structure which is a popular these days, distributed ledger structure. There are some studies which are about this topic especially on the bitcoin side, nevertheless there exists some studies on the databases part, too. On the perspective of these studies, I created a distributed ledger using one of the Machine Learning algorithms on the proof of work part which deters denial-of-service attacks and other service abuses as spam. The algorithm I used as proof of work is Singular Value Decomposition algorithm. The client submits vulnerabilities to database, then mines the submissions. If the validation is completed by reconstruction decomposed image for every guide which is determined by server beginning of the client request, the block is created and this block will be added to vulnerability tree.

Poster: https://drive.google.com/file/d/1N1p6-iOuch0_8044iBNZ3ElWk_Z0w7RG/view?usp=sharing

Video: https://drive.google.com/file/d/1eWtlCtpJYOw0ROfcx5L33SeUqL_UfOgJ/view?usp=sharing