Machine Learning (In) Security: A Stream of Problems
arXiv:2010.16045 · doi:10.1145/3617897
Abstract
Machine Learning (ML) has been widely applied to cybersecurity and is considered state-of-the-art for solving many of the open issues in that field. However, it is very difficult to evaluate how good the produced solutions are, since the challenges faced in security may not appear in other areas. One of these challenges is the concept drift, which increases the existing arms race between attackers and defenders: malicious actors can always create novel threats to overcome the defense solutions, which may not consider them in some approaches. Due to this, it is essential to know how to properly build and evaluate an ML-based security solution. In this paper, we identify, detail, and discuss the main challenges in the correct application of ML techniques to cybersecurity data. We evaluate how concept drift, evolution, delayed labels, and adversarial ML impact the existing solutions. Moreover, we address how issues related to data collection affect the quality of the results presented in the security literature, showing that new strategies are needed to improve current solutions. Finally, we present how existing solutions may fail under certain circumstances, and propose mitigations to them, presenting a novel checklist to help the development of future ML solutions for cybersecurity.
References in corpus (29)
- Scikit-learn: Machine Learning in Python
- SMOTE: Synthetic Minority Over-sampling Technique
- Efficient Estimation of Word Representations in Vector Space
- Distributed Representations of Words and Phrases and their Compositionality
- Explaining and Harnessing Adversarial Examples
- Going Deeper with Convolutions
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- Transfusion: Understanding Transfer Learning for Medical Imaging
- Challenges in Deploying Machine Learning: a Survey of Case Studies
- Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
- Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
- The Role of Machine Learning in Cybersecurity
- DeepSign: Deep Learning for Automatic Malware Signature Generation and Classification
- Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning
- Active Authentication on Mobile Devices via Stylometry, Application Usage, Web Browsing, and GPS Location
- Simple Black-box Adversarial Attacks
- EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
- Practical Black-Box Attacks against Machine Learning
- Towards Adversarial Malware Detection: Lessons Learned from PDF-based Attacks
- The Limitations of Deep Learning in Adversarial Settings
- Machine Learning Security in Industry: A Quantitative Survey
- SoK: The Impact of Unlabelled Data in Cyberthreat Detection
- Deep Transfer Learning for Static Malware Classification
- SoK: Applying Machine Learning in Security - A Survey
- Non-Negative Networks Against Adversarial Attacks
- Feature Hashing for Large Scale Multitask Learning
- A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer Learning
- Neurlux: Dynamic Malware Analysis Without Feature Engineering
- Garbage In, Garbage Out? Do Machine Learning Application Papers in Social Computing Report Where Human-Labeled Training Data Comes From?