Recent Work


Machine Code Metamorphism using Recurrent Neural Networks

Code metamorphism is a dynamic approach of obfuscation in which a program refactors itself at run time while preserving its semantics. This paper presents a new metamorphic framework based on a predictive model


When you should use Constraint Solvers instead of Machine Learning

Machine Learning and Deep Learning are ongoing buzzwords in the industry. Branding ahead of functionalities led to Deep Learning being overused in many artificial intelligence applications.


Statistical Decision Theory for Predictive Models

Can you write a predictive function from observations which would minimize the error deviation? Or the average error? Can you find the best theoretical predictor which would minimize any given loss function?


Beware of the AI hype

An Australian PhD candidate in artificial intelligence made a recent post on LinkedIn about his researches on SARS-CoV-2. The post gathered thousands of views, likes, and shares.


Optional: A Library for the R Programming Language

This library package aims to add abilities to the R programming language such as nullable types and pattern matching in order to benefit from the functional programming paradigm.