The manuscript “Machine learning methods for speech emotion recognition on telecommunication systems” is devoted to the study of human behavior in stressful situations using machine learning methods. In the work, the authors analyzed the photoplethysmogram obtained from a smart bracelet and the photoplethysmogram obtained from a polygraph. This data allowed the authors to train a neural network using polygraph data to constantly monitor a person’s emotional state based on data from a smart bracelet; this approach identifies a state of panic stupor. The authors also propose a method for tracking such conditions in real time by synchronizing a smart bracelet with a smartphone. Using the method in combination with existing methods of combating telephone scammers will significantly increase the effectiveness of this fight. The method proposed by the authors can find wide application in cyber-physical systems for detecting illegal actions.

In the article “Machine learning methods for the industrial robotic systems security” the authors propose a new approach to ensuring the safety of objects in protected areas, using the example of a parking lot, using an ensemble of computer vision algorithms and the mathematical apparatus of convolutional neural networks. An important practical problem of classifying images of vehicles according to various semantic features is being solved. Test studies of the models showed good identification of semantic signs of damage caused by the attacker, and also demonstrated good quality metrics for machine learning models. The implemented ANN models can be used to control a mobile security robot.

The article “Comparison of the effectiveness of cepstral coefficients for Russian speech synthesis detection”, the authors analyze the effectiveness of cepstral coefficients used in the fight against voice spoofing. A new dataset containing both real and synthesized Russian speech is proposed. The new data set is used to train two types of neural networks, CNN and LSTM. The work solves the current problem of determining speech synthesis in the case of deepfakes in the Russian language.

The research work “Parametric study of hand dorsal vein biometric recognition vulnerability to spoofing attacks” is devoted to the security of biometric hand vein recognition systems. The authors analyze the effectiveness of various types of presentation attacks. The study results demonstrate serious risks to biometric systems based on vein pattern modality.

The authors of the work “Potential cyber threats of adversarial attacks on autonomous driving models” explore potential cyber threats to the main components of unmanned vehicles. Due to the fact that many components of the driving system are based on machine learning models, they are vulnerable to attacks by intruders. The authors generated a dataset with images of road signs; during the experiment, the original images were distorted and used to train classification models based on deep neural networks. The authors demonstrated the cyber threats of adversarial attacks on autonomous driving models.

The article “Forecasting of digital financial crimes in Russia based on machine learning methods” is devoted to the development of an ensemble forecasting system based on machine learning methods to predict the number of digital financial crimes. The ensemble model consists of five forecasting methods. The model includes wavelet forecast and exponential forecasting method. Advanced artificial intelligence-based forecasting technology for financial market looks as a promising research area.

Separately, we would like to note the article “Next Gen Cybersecurity Paradigm Towards Artificial General Intelligence: Russian Market Challenges and Future Global Technological Trends”, which examines the theoretical foundations of the new cybersecurity paradigm based on artificial intelligence in combination with the basic principles of the improvement system NIST critical infrastructure cybersecurity and new LLM opportunities.

The submitted materials were carefully selected and reviewed by three independent anonymous reviewers. The decision to publish the submitted materials was made by the guest editors and the editor-in-chief.

The editors would like to thank:

  • Authors—for submitting scientific articles and for their efforts to finalize them;

  • Reviewers—for their careful work on the materials of the article;

  • The Springer team—for prompt technical support and attention to the process.

We sincerely thank the Editor-in-Chief, Professor Eric Filiol, for the opportunity to present works of Russian researchers in the Journal of Computer Virology and Hacking Techniques.

We express special words of gratitude to Professor Vladimir Fomichev, who not only contributed to the international academic cooperation development, but also to the technological partnership for leading research scientists and the Russian information security industry.