Skip to main navigation
Skip to search
Skip to main content
Welcome to DTU Research Database Home
About DTU Orbit
Home
Profiles
Research units
Publications
Activities
Projects
Prizes
Press/Media
Datasets
Search by expertise, name or affiliation
A study of Adversarial Machine Learning for Cybersecurity
Sam Afzal-Houshmand
Cybersecurity Engineering
Department of Applied Mathematics and Computer Science
Research output
:
Book/Report
›
Ph.D. thesis
216
Downloads (Pure)
Overview
Fingerprint
Projects
(1)
Fingerprint
Dive into the research topics of 'A study of Adversarial Machine Learning for Cybersecurity'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Computer Science
Adversarial Machine Learning
100%
Artificial Intelligence
33%
Botnets
11%
Central Objective
11%
Classification Framework
11%
Classification Models
11%
Collected Data
11%
Computational Efficiency
11%
Critical Application
11%
Cybersecurity
100%
Data Provenance
11%
Data Structure
11%
Decision-Making
11%
Deep Learning
44%
Deep Learning Technique
22%
Denial-of-Service
11%
Domain Name Server
100%
Enhanced Security
11%
Explainable Artificial Intelligence
11%
Internet of Things
11%
Intrusion Detection
11%
Large Data Set
11%
Machine Learning
88%
Machine Learning Technique
11%
Malicious Actor
11%
Malicious Attack
11%
Malicious Domain
33%
Man-in-the-Middle Attack
11%
Networking Environment
11%
Ontology
22%
Related Concept
11%
Research Project
11%
Safety Critical Systems
11%
Security Awareness
22%
Spoofing
22%
Keyphrases
Adversarial Classification
11%
Belief Inference
11%
Cache Poisoning
11%
Domain Hijacking
11%
Domain Name System
100%
Generic Classification
11%
Hostname
11%
Intelligence Science
11%
Malicious Domain Name
22%
Malicious Domains
11%
Mobile Crowdsourcing
11%