Machine Learning in Cyber-Security - Problems, Challenges and Data Sets
arXiv:1812.07858
Abstract
We present cyber-security problems of high importance. We show that in order to solve these cyber-security problems, one must cope with certain machine learning challenges. We provide novel data sets representing the problems in order to enable the academic community to investigate the problems and suggest methods to cope with the challenges. We also present a method to generate labels via pivoting, providing a solution to common problems of lack of labels in cyber-security.
References in corpus (8)
- Frustratingly Easy Domain Adaptation
- Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
- Microsoft Malware Classification Challenge
- Predicting Domain Generation Algorithms with Long Short-Term Memory Networks
- A Berkeley View of Systems Challenges for AI
- EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
- Unsupervised Deep Embedding for Clustering Analysis
- eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys
Cited by in corpus (6)
- A Taxonomy of Network Threats and the Effect of Current Datasets on Intrusion Detection Systems
- Graph link prediction in computer networks using Poisson matrix factorisation
- Fast likelihood-based change point detection
- Follow Your Nose -- Which Code Smells are Worth Chasing?
- ComSum: Commit Messages Summarization and Meaning Preservation
- Semisupervised Adversarial Neural Networks for Cyber Security Transfer Learning