Are Malware Detection Classifiers Adversarially Vulnerable to Actor-Critic based Evasion Attacks?

Hemant Rathore; Sujay C Sharma; Sanjay K. Sahay; Mohit Sewak

doi:10.4108/eai.31-5-2022.174087

ScienceGate Book Chapters

JOURNAL ARTICLE

Are Malware Detection Classifiers Adversarially Vulnerable to Actor-Critic based Evasion Attacks?

Hemant Rathore Sujay C Sharma Sanjay K. Sahay Mohit Sewak

Year: 2022 Journal: ICST Transactions on Scalable Information Systems Pages: 174087-174087 Publisher: European Alliance for Innovation

DOI: 10.4108/eai.31-5-2022.174087

Get Full-Text PDF Get Analytical Report

Abstract

The European Union Digital Library (EUDL) is the central repository for all content published by the different branches of the European Alliance for Innovation (EAI). EUDL also hosts or indexes content from selected partner or member organizations and affiliates.

Keywords:

Evasion (ethics) Malware Computer science Computer security Artificial intelligence Machine learning Biology Genetics

Metrics

Cited By

1.36

FWCI (Field Weighted Citation Impact)

Refs

0.75

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Advanced Malware Detection Techniques

Physical Sciences → Computer Science → Signal Processing

Network Security and Intrusion Detection

Physical Sciences → Computer Science → Computer Networks and Communications

Adversarial Robustness in Machine Learning

Physical Sciences → Computer Science → Artificial Intelligence

Are Malware Detection Classifiers Adversarially Vulnerable to Actor-Critic based Evasion Attacks?

Abstract

Metrics

Citation History

Topics

Related Documents

Efficient Adversarially Guided Actor–Critic

Defending malware detection models against evasion based adversarial attacks

Defending Malware Detection Models Against Evasion Based Adversarial Attacks

Defending Evasion Attacks via Adversarially Adaptive Training

Quantifying the impact of adversarial evasion attacks on machine learning based android malware classifiers