Development of an Adapter for Analyzing and Protecting Machine Learning Models from Competitive Activity in the Networks Services

2025/05/01 by Denis Parfenov, Parfenov, Denis, Anton Parfenov +1
Business, Management and Accounting · Engineering · Social Sciences · #Advanced Research in Systems and Signal Processing #Cryptography and Security (cs.CR) #Economic and Technological Systems Analysis #FOS: Computer and information sciences #Legal and Policy Issues #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2505.01460

openalex publication_date 2025/05/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Due to the increasing number of tasks that are solved on remote servers, identifying and classifying traffic is an important task to reduce the load on the server. There are various methods for classifying traffic. This paper discusses machine learning models for solving this problem. However, such ML models are also subject to attacks that affect the classification result of network traffic. To protect models, we proposed a solution based on an autoencoder

Citations

• Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
• Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder
• Adversarial Machine Learning Security Problems for 6G: mmWave Beam Prediction Use-Case

Related

• On Designing Machine Learning Models for Malicious Network Traffic Classification
• Robustifying ML-powered Network Classifiers with PANTS
• Cruise Control: Dynamic Model Selection for ML-Based Network Traffic Analysis
• Discriminative models for multi-instance problems with tree-structure
• Detecting Abnormal Traffic in Large-Scale Networks