Summary of Cbr — Boosting Adaptive Classification by Retrieval Of Encrypted Network Traffic with Out-of-distribution, By Amir Lukach et al.
CBR – Boosting Adaptive Classification By Retrieval of Encrypted Network Traffic with Out-of-distribution
by Amir Lukach, Ran Dubin, Amit Dvir, Chen Hajaj
First submitted to arxiv on: 17 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Networking and Internet Architecture (cs.NI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to encrypted network traffic classification called Adaptive Classification By Retrieval (CBR). The current methods for handling unknown classes rely on retraining the model, which is resource-intensive and time-consuming. To address this issue, CBR uses an ANN-based method that can detect new and existing classes without retraining the model. The proposed approach achieved similar results to Random Forest (RF) with up to 5% difference in classification tasks, while having a slight decrease in performance for new samples from new classes. Moreover, CBR can be used as a complementary solution alongside RF or other machine/deep learning classification methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computers better at sorting and identifying different types of internet traffic without needing to update the computer’s knowledge all the time. Right now, computers use machine learning to sort this traffic into categories, but when they encounter something new, they often don’t know what it is. The researchers came up with a new way to do this called Adaptive Classification By Retrieval (CBR). It uses artificial neural networks and can figure out what kind of internet traffic something is without needing to be updated. This makes it faster and more efficient than the current methods. |
Keywords
* Artificial intelligence * Classification * Deep learning * Machine learning * Random forest
