Binary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Model

12/14/2020
by   MohammadReza Ebrahimi, et al.
0

Anti-malware engines are the first line of defense against malicious software. While widely used, feature engineering-based anti-malware engines are vulnerable to unseen (zero-day) attacks. Recently, deep learning-based static anti-malware detectors have achieved success in identifying unseen attacks without requiring feature engineering and dynamic analysis. However, these detectors are susceptible to malware variants with slight perturbations, known as adversarial examples. Generating effective adversarial examples is useful to reveal the vulnerabilities of such systems. Current methods for launching such attacks require accessing either the specifications of the targeted anti-malware model, the confidence score of the anti-malware response, or dynamic malware analysis, which are either unrealistic or expensive. We propose MalRNN, a novel deep learning-based approach to automatically generate evasive malware variants without any of these restrictions. Our approach features an adversarial example generation process, which learns a language model via a generative sequence-to-sequence recurrent neural network to augment malware binaries. MalRNN effectively evades three recent deep learning-based malware detectors and outperforms current benchmark methods. Findings from applying our MalRNN on a real dataset with eight malware categories are discussed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/16/2023

Query-Free Evasion Attacks Against Machine Learning-Based Malware Detectors with Generative Adversarial Networks

Malware detectors based on machine learning (ML) have been shown to be s...
research
12/03/2021

Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approach

Deep Learning (DL)-based malware detectors are increasingly adopted for ...
research
10/25/2022

Multi-view Representation Learning from Malware to Defend Against Adversarial Variants

Deep learning-based adversarial malware detectors have yielded promising...
research
12/08/2022

PKDGA: A Partial Knowledge-based Domain Generation Algorithm for Botnets

Domain generation algorithms (DGAs) can be categorized into three types:...
research
11/06/2019

The Naked Sun: Malicious Cooperation Between Benign-Looking Processes

Recent progress in machine learning has generated promising results in b...
research
07/19/2018

Emulating malware authors for proactive protection using GANs over a distributed image visualization of the dynamic file behavior

Malware authors have always been at an advantage of being able to advers...
research
07/19/2018

Emulating malware authors for proactive protection using GANs over a distributed image visualization of dynamic file behavior

Malware authors have always been at an advantage of being able to advers...

Please sign up or login with your details

Forgot password? Click here to reset