Shellcode_IA32: A Dataset for Automatic Shellcode Generation

TL;DR

This paper introduces Shellcode_IA32, a new dataset linking assembly instructions with natural language descriptions to facilitate automatic shellcode generation using neural machine translation techniques.

Contribution

It provides the first dataset of its kind for shellcode generation and establishes baseline performance with standard NMT methods.

Findings

Baseline performance levels established for shellcode generation

Dataset includes challenging and common assembly instructions

First dataset linking assembly code with natural language descriptions

Abstract

We take the first step to address the task of automatically generating shellcodes, i.e., small pieces of code used as a payload in the exploitation of a software vulnerability, starting from natural language comments. We assemble and release a novel dataset (Shellcode_IA32), consisting of challenging but common assembly instructions with their natural language descriptions. We experiment with standard methods in neural machine translation (NMT) to establish baseline performance levels on this task.