×

You are using an outdated browser Internet Explorer. It does not support some functions of the site.

Recommend that you install one of the following browsers: Firefox, Opera or Chrome.

Contacts:

+7 961 270-60-01
ivdon3@bk.ru

  • Using Clustering Methods to Automate the Formation of User Roles

    The article solves the problem of automated generation of user roles using machine learning methods. To solve the problem, cluster data analysis methods implemented in Python in the Google Colab development environment are used. Based on the results obtained, a method for generating user roles was developed and tested, which allows reducing the time for generating a role-based access control model.

    Keywords: machine learning, role-based access control model, clustering, k-means method, hierarchical clustering, DBSCAN method

  • Detection of false positive cybersecurity incidents based on artificial neural networks

    The possibility of detecting false positive cybersecurity incidents using deep learning models - GRU, Bidirectional LSTM (Bi-LSTM), LSTM - has been studied. The results obtained demonstrate the effectiveness of solving the problem for Powershell scripts. The Bi-LSTM model showed the best classification results, demonstrating an accuracy of 98.50% on the test sample.

    Keywords: machine learning, classification, cybersecurity, deep learning, Powershell

  • Intelligent detection of steganography transform based on containers classification

    The possibility of detection of steganography in digital images based on the classification of stegocontainers is investigated. The obtained results demonstrate the effectiveness of using deep neural networks for solving this problem. The LSB method can be detected using EfficientNet b3 architecture. The achieved classification accuracy is above 97%. Using of steganography methods in frequency domain can be effectively detected by classifying their representation in the form of a digital YCrBr model, with augmentation (vertical and horizontal rotations). The classification accuracy is above 77%.

    Keywords: Steganography, stegocontainer, machine learning, classification, digital image, deep learning, CNN, EfficientNet b3, confidentiality, information protection

  • Approach for implementation of stream cipher based on fuzzy pseudo-random secquences generator

    An approach for cosntruction of stream ciphers based on new type of cipher gamma generators with a non-linear (fuzzy) shift register selection function is proposed. The best configuration of generator is selected for generating a gamma whose properties are closest to white noise. It is shown that the proposed approach makes it possible to generate a gamma sequence with a quality that exceeds a number of other classical generators.

    Keywords: cryptography, stream cipher, gamma, PNSG, random test, fuzzy logic,membership function, linguistic variable, defuzzification, linear feedback shift register

  • Reverse analysis of malware Raccoon Stealer

    We describe the process and results of reverse analysis of malware Raccoon Stealer v.1.7.3. We describe instruments of analysis, the process of code analysis, unpacking, getting of original code. We describe the process of code analysis, construction of malware working algorithm. We describe recomendations for defense from Raccoon Stealer.

    Keywords: Reverse analysis, reverse engineering, malware, code analysis, debuger, disassembler, hex redactor, database, browser, information security