Research at the intersection of machine learning, programming languages, and software
engineering has recently taken important steps in proposing learnable probabilistic models …

In the age of increasing mobile and smart connectivity, malware poses an ever evolving
threat to individuals, societies and nations. Anti-malware companies are often the first and …

A transcompiler, also known as source-to-source translator, is a system that converts source
code from a high-level programming language (such as C++ or Python) to another …

Learning tasks on source code (ie, formal languages) have been considered recently, but
most work has tried to transfer natural language methods and does not capitalize on the …

Most existing Android malware detection and categorization techniques are static
approaches, which suffer from evasion attacks, such as obfuscation. By analyzing program …

Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two
complementary representations of the same computer program. Traditionally, designers of …

Predicting program properties such as names or expression types has a wide range of
applications. It can ease the task of programming, and increase programmer productivity. A …

Recent advances in self-supervised learning have dramatically improved the state of the art
on a wide variety of tasks. However, research in language model pre-training has mostly …

In the last decade, machine-learning-based compilation has moved from an obscure
research niche to a mainstream activity. In this paper, we describe the relationship between …

Every programmer has a characteristic style, ranging from preferences about identifier
naming to preferences about object relationships and design patterns. Coding conventions …