Practical Attacks on Machine Learning: A Case Study on Adversarial Windows Malware

Luca Demetrio, Battista Biggio, Fabio Roli
7/12/2022
cs.CRcs.LG

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

While machine learning is vulnerable to adversarial examples, it still lacks systematic procedures and tools for evaluating its security in different application contexts. In this article, we discuss how to develop automated and scalable security evaluations of machine learning using practical attacks, reporting a use case on Windows malware detection.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Machine Learning Security in Industry: A Quantitative Survey

89% match2022

Review on the Feasibility of Adversarial Evasion Attacks and Defenses for Network Intrusion Detection Systems

88% match2023

Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systems

87% match2023

Machine Learning for Windows Malware Detection and Classification: Methods, Challenges and Ongoing Research

87% match2024

AI Product Security: A Primer for Developers

87% match2023

How Real Is Real? A Human Evaluation Framework for Unrestricted Adversarial Examples

87% match2024

Cite this paper

@article{demetrio2022practical,
  title  = {Practical Attacks on Machine Learning: A Case Study on Adversarial Windows Malware},
  author = {Luca Demetrio and Battista Biggio and Fabio Roli},
  year   = {2022},
  eprint = {2207.05548},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.05548v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.05548.svg)](https://codeofpaper.com/paper/2207.05548)

Discussion