Malicious PDF Detection Model against Adversarial Attack Built from Benign PDF Containing JavaScript

Abstract

Intelligent attacks using document-based malware that exploit vulnerabilities in document viewing software programs or document file structure are increasing rapidly. There are many cases of using PDF (portable document format) in proportion to its usage. We provide in-depth analysis on PDF structure and JavaScript content embedded in PDFs. Then, we develop the diverse feature set encompassing the structure and metadata such as file size, version, encoding method and keywords, and the content features such as object names, keywords, and readable strings in JavaScript. When features are diverse, it is hard to develop adversarial examples because small changes are robust for machine-learning algorithms. We develop a detection model using black-box type models with the structure and content features to minimize the risk of adversarial attacks. To validate the proposed model, we design the adversarial attack. We collect benign documents containing multiple JavaScript codes for the base of adversarial samples. We build the adversarial samples by injecting the malware codes into base samples. The proposed model is evaluated against a large collection of malicious and benign PDFs. We found that random forest, an ensemble algorithm of a decision tree, exhibits a good performance on malware detection and is robust for adversarial samples.