Black-box Adversarial Machine Learning Attack on Network Traffic Classification
| Title | Black-box Adversarial Machine Learning Attack on Network Traffic Classification |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Usama, Muhammad, Qayyum, Adnan, Qadir, Junaid, Al-Fuqaha, Ala |
| Conference Name | 2019 15th International Wireless Communications Mobile Computing Conference (IWCMC) |
| Date Published | June 2019 |
| Publisher | IEEE |
| ISBN Number | 978-1-5386-7747-6 |
| Keywords | Adversarial Machine Learning, adversarial perturbations, adversarial threats, autonomous networks, Black Box Security, black-box adversarial attack, black-box adversarial machine, composability, computer network security, Data models, deep machine learning models, deep machine learning techniques, deep machine learning-based classifiers, learning (artificial intelligence), machine learning, Metrics, Network traffic classification, Neural networks, pattern classification, Perturbation methods, pubcrawl, resilience, Resiliency, security, security threat, Support vector machines, telecommunication computing, telecommunication traffic, Training |
| Abstract | Deep machine learning techniques have shown promising results in network traffic classification, however, the robustness of these techniques under adversarial threats is still in question. Deep machine learning models are found vulnerable to small carefully crafted adversarial perturbations posing a major question on the performance of deep machine learning techniques. In this paper, we propose a black-box adversarial attack on network traffic classification. The proposed attack successfully evades deep machine learning-based classifiers which highlights the potential security threat of using deep machine learning techniques to realize autonomous networks. |
| URL | https://ieeexplore.ieee.org/document/8766505 |
| DOI | 10.1109/IWCMC.2019.8766505 |
| Citation Key | usama_black-box_2019 |
- machine learning
- Training
- telecommunication traffic
- telecommunication computing
- Support vector machines
- security threat
- security
- Resiliency
- resilience
- pubcrawl
- Perturbation methods
- pattern classification
- Neural networks
- Network traffic classification
- Metrics
- Adversarial Machine Learning
- learning (artificial intelligence)
- deep machine learning-based classifiers
- deep machine learning techniques
- deep machine learning models
- Data models
- computer network security
- composability
- black-box adversarial machine
- black-box adversarial attack
- Black Box Security
- autonomous networks
- adversarial threats
- adversarial perturbations