Evading Machine Learning Malware Detection

By H. S. Anderson. 2017

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Adversarial Examples: Attacks and Defenses for Deep Learning (2017, background): “[93] used a large number of features (2350) to cover the required feature space of portable executable (PE) files.”
Exploring Backdoor Poisoning Attacks Against Malware Classifiers (2020, background): “[9], which trains Reinforcement Learning agents to generate functionality preserving mutations of a binary.”
Identify Susceptible Locations in Medical Records via Adversarial Attacks on Deep Predictive Models (2018, methodology): “[3, 21] used GAN based algorithm and [2] used reinforcement learning to generate adversarial examples.”
Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables (2018, background): “, [5]), it is common to consider that it is not trivial to practically implement the same attack on executable files [2], [18], [25], as one mistake at changing the code section or the headers may completely compromise the file functionality.”
Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning (2018, background): “We previously released a whitepaper [1] that initially demonstrated these results.”
Robust Intelligent Malware Detection Using Deep Learning (2019, background): “Moreover, once an attacker comes to know the features, the malware detector can be evaded easily [14].”
Naive Bayes: applications, variations and vulnerabilities: a review of literature with code snippets for implementation (2020, background): “Machine learning can be considered as popular approach to address signatureless intrusion detection due to the ability of generalizing both malware families and polymorphic strains that have never before seen (Anderson et al. 2017).”