Search

Search Results

• GAME-THEORETIC AND REINFORCEMENT LEARNING-BASED ALGORITHM FOR INTENTIONAL JAMMING MITIGATION

  К. S. Grigoryan , Е. S. Basan

  66-77

  2026-09-10

  Abstract ▼

  Intentional jamming represents a serious threat to the security and availability of wireless communication systems. Modern wireless networks, including cognitive radio, sensor networks, and Internet of Things infrastructures, are particularly vulnerable because adversaries can dynamically adapt their jamming strategies. The objective of this study is to develop an adaptive anti-jamming algorithm capable of maintaining communication reliability under dynamic interference conditions. To achieve this goal, the interaction between the legitimate transmitter and the jammer is modeled as a Markov Stackelberg game, where the legitimate node acts as a leader and the jammer acts as a follower. Reinforcement learning is used to determine the optimal strategy of the leader in a stochastic environment, while robustness against channel uncertainty is ensured through a SOCP (Second-order cone programming) formulation that guarantees the required quality-of-service constraints. The learning process is implemented using the SAC (Soft Actor-Critic) algorithm, which enables stable policy optimization in continuous action spaces and stochastic environments.
  The research tasks include the formalization of the anti-jamming interaction as a Markov decision process, the integration of reinforcement learning with a robust SOCP optimization layer, and the evaluation of the proposed approach through simulation. A Monte Carlo simulation of the proposed algorithm, as well as several algorithms based on FHSS (Frequency-Hopping Spread Spectrum), was conducted. The proposed anti-jamming algorithm reduces the probability of communication outage by 0.14. The results indicate that the proposed approach improves the resilience of wireless communication systems and reduces the probability of successful denial-of-service attacks at the physical layer

• IMPROVING THE EFFICIENCY OF HIGH-PERFORMANCE FREE SPACE OPTICAL COMMUNICATION CHANNELS IN VARIOUS WEATHER CONDITIONS

  S. V. Zhilin, V.V. Arkhipenko, Е.S. Basan, М.Y. Polenov

  114-126

  2025-08-01

  Abstract ▼

  A common problem of traditional radio communication channels - the lack of free frequencies,
  noise, low bandwidth, the need to obtain a license to use the frequency, the relative ease of hacking.
  Free space optical communication channels overcome these limitations, is one of the types of communication
  systems that use open space to transmit information carried by light - this points to the
  need for direct visibility of the transceivers. Due to the influence of various weather conditions, the
  light flux is subject to atmospheric attenuation. In this paper, a method to improve the efficiency of
  high-performance wireless optical communication channels in different weather conditions: clear
  sky, fog, rain and snow was investigated. The existing wireless optical communication technology, a
  dense multiplexing multiplexing (DWDM) system with one input and one output (SISO), was considered.
  And it was proposed to improve the existing system by applying multiple input/output (MIMO).
  An impact and attenuation analysis on the wireless optical network in different weather conditions was conducted. The study was based on the use of the Optisystem simulation software toolkit, which
  is used to emulate different weather conditions of attenuation in two types of systems. Models were
  developed for each of the optical communication systems studied. A comparison between SISO and
  MIMO systems is made in terms of quality factor under different weather conditions. The proposed
  system shows promising results in terms of performance and received signal quality. The transmission
  path length of the proposed system in dense fog conditions increases by 33.6%. The transmission
  path length of the proposed system in heavy rain increases by 63.89%. The transmission path
  length of the proposed system in heavy snow increases by 35,21%.

• RESEARCH OF MACHINE LEARNING METHODS FOR DETECTING SPOOFING ATTACKS IN DECENTRALIZED NETWORKS

  М.А. Lapina , R.А. Dymuha , N.N. Kucherov , Е.S. Basan

  16-31

  2025-07-24

  Abstract ▼

  Unmanned aerial vehicles are appearing more and more in our lives and are used for various purposes such as cargo delivery, monitoring, household management, exploration and entertainment. But along with their growing popularity, the number of people who intentionally want to interfere with the operation of UAVs and use them for their own interests and purposes is also increasing. They use various types of attacks to eliminate or intercept the drone by any means. Spoofing attacks are one of the most common and dangerous types of attacks, as they allow attackers to act unnoticed, faking the identifiers of autonomous aircraft or operators, posing as legitimate participants in the system. The purpose of such attacks may be to intercept control, steal data, sabotage, or use UAVs to perform malicious actions such as espionage, damage, or malfunction operations. But every year it becomes more difficult to prevent attacks, as they are difficult to detect and can lead to serious consequences, which is why such a solution as detecting spoofing attacks on an unmanned vehicle using machine learning was invented. The article discusses spoofing attacks on UAVs, analyzes spoofing on autonomous aircraft, and studies machine learning methods for detecting spoofing attacks based on a dataset using the Knime platform. The results of the study demonstrate that the method of detecting attacks using machine learning based on the ensemble method, the Tree Ensemble Learner and Random Forest Learner models, which showed results of 97.110% and 97.039%, respectively, is the best among other methods, which will improve the security of unmanned aerial vehicles, reduce the burden on operators and increase the reliability of the system as a whole. In the future, the proposed approach can be expanded to detect other types of cyberattacks, which will make it a universal method of protection against intruders