Stack-based Buffer Overflow Detection using Recurrent Neural Networks (2020-12-30T00:00:00.000000Z)

TL;DR

The results show that the architecture is able to capture subtle stack-based buffer overflow vulnerabilities that strongly depend on the context, thus suggesting that this approach may be extended to real-world setting, as well as to other forms of vulnerability detection.

Abstract

Detecting vulnerabilities in software is a critical challenge in the development and deployment of applications. One of the most known and dangerous vulnerabilities is stack-based buffer overflows, which may allow potential attackers to execute malicious code. In this paper we consider the use of modern machine learning models, specifically recurrent neural networks, to detect stack-based buffer overflow vulnerabilities in the assembly code of a program. Since assembly code is a generic and common representation, focusing on this language allows us to potentially consider programs written in several different programming languages. Moreover, we subscribe to the hypothesis that code may be treated as natural language, and thus we process assembly code using standard architectures commonly employed in natural language processing. We perform a set of experiments aimed at confirming the validity of the natural language hypothesis and the feasibility of using recurrent neural networks for detecting vulnerabilities. Our results show that our architecture is able to capture subtle stack-based buffer overflow vulnerabilities that strongly depend on the context, thus suggesting that this approach may be extended to real-world setting, as well as to other forms of vulnerability detection.

Authors

W. A. Dahl

1 papers

László Erdodi

1 papers

Fabio Massimo Zennaro

1 papers

TL;DR

Abstract

Authors

References30 items

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Layered Object-Oriented Programming: Advanced VTable Reuse Attacks on Binary-Level Defense

Automated Vulnerability Detection in Source Code Using Deep Representation Learning

EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models

VulDeePecker: A Deep Learning-Based System for Vulnerability Detection

Vulnerability detection with deep learning

Malware Detection by Eating a Whole EXE

A Survey of Machine Learning for Big Code and Naturalness

Attention is All you Need

The WannaCry ransomware attack

Collective Anomaly Detection Based on Long Short-Term Memory Recurrent Neural Networks

Toward Large-Scale Vulnerability Discovery using Machine Learning

Predicting Vulnerable Software Components through N-Gram Analysis and Statistical Feature Selection

Effective Approaches to Attention-based Neural Machine Translation

A Method for Detecting Abnormal Program Behavior on Embedded Devices

ImageNet classification with deep convolutional neural networks

Software vulnerability prediction using text analysis techniques

Vulnerability Extrapolation: Assisted Discovery of Vulnerabilities Using Machine Learning

Long Short-Term Memory

Control-flow Enforcement Technology Specification, Intel Corporation

The National In Security Agency

Ms17-010 eternalblue smb remote windows kernel pool corruption

The Shadow Brokers

Using as assembler directives

The National Cybersecurity FFRDC. Common vulnerabilities and exposures

Binary ninja

received his PhD in Machine Learning from Manchester

Sourcefire vulnerability research team (vrt)

Gcc wiki

Ida pro -hex rays

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names