METHOD AND SYSTEM FOR MODIFYING PROGRAM CODE Russian patent published in 2024 - IPC G06F8/30 

Abstract RU 2824522 C1

FIELD: information technology.

SUBSTANCE: invention relates to an automated method and a system for modifying program code using machine learning algorithms. Method is carried out using at least one processor and comprises steps of: obtaining data containing at least a block of source code; source code is converted into a program code graph, in which internal vertices are associated with programming language operators, and leaves with corresponding operands; performing the program code graph processing using the machine learning (ML) coding model, trained on the program code graphs, in the course of which a representation of the program code graph in the form of a matrix of hidden states is obtained; method includes processing a matrix of hidden states using a generative machine learning (ML) model, trained on matrices of hidden states of graphs of the unmodified program code, graphs of the modified code and their source codes, in the course of which a new program code graph is obtained, corresponding to the modified program code, which is equivalent to the original program code in terms of functions performed; the program code graph obtained at the previous step is converted into a block of modified source code, which is functionally equivalent to the initial block of the source code.

EFFECT: high rate of modifying program code owing to automation of the process.

7 cl, 2 dwg

Similar patents RU2824522C1

Title Year Author Number
METHOD AND SYSTEM FOR ELIMINATING VULNERABILITIES IN PROGRAM CODE 2023
  • Vyshegorodtsev Kirill Evgenevich
  • Kuzmin Aleksandr Mikhajlovich
RU2821220C1
METHOD AND SYSTEM FOR IDENTIFYING EXPLOITED VULNERABILITIES IN THE PROGRAM CODE 2022
  • Maksimova Anna Andreevna
  • Goncharenko Lejla Khalidovna
  • Bachevskij Artem Evgenevich
  • Gurtova Kristina Sergeevna
  • Umerenko Grigorij Sergeevich
  • Anistratenko Mikhail Arturovich
RU2790005C1
METHOD AND SYSTEM FOR SUPPORTING MEDICAL DECISION MAKING USING MATHEMATICAL MODELS OF PRESENTING PATIENTS 2017
  • Drokin Ivan Sergeevich
  • Bukhvalov Oleg Leonidovich
  • Sorokin Sergej Yurevich
RU2703679C2
METHOD AND SYSTEM FOR AUTOMATED MIGRATION OF INFORMATION INFRASTRUCTURE OF AN ENTERPRISE TO A CLOUD SERVICE 2022
  • Khapov Igor Aleksandrovich
  • Krivtsova Ekaterina Nikolaevna
  • Kistauri David Vyacheslavovich
  • Sajnukov Mikhail Sergeevich
  • Mindzaeva Dana Yanovna
  • Komarov Roman Andreevich
  • Khaliulov Albert Rashidovich
RU2792257C1
METHOD AND SYSTEM FOR DETECTING MALICIOUS FILES IN A NON-ISOLATED MEDIUM 2020
  • Prudkovskij Nikolaj Sergeevich
RU2722692C1
METHOD TO PREVENT REVERSE ENGINEERING OF SOFTWARE, UNAUTHORISED MODIFICATION AND DATA CAPTURE DURING PERFORMANCE 2006
  • Asipov Keren
  • Asipov Boris
RU2439669C2
METHOD AND SYSTEM OF GRAPHICAL ORIENTED CREATION OF SCALABLE AND SUPPORTED SOFTWARE REALIZATIONS OF COMPLEX COMPUTATIONAL METHODS 2017
  • Alexander Pavlovich Sokolov
  • Pershin Anton Yurevich
RU2681408C2
METHOD FOR DIAGNOSING AIRCRAFT ON-BOARD EQUIPMENT COMPLEX BASED ON MACHINE LEARNING 2023
  • Bukirev Aleksandr Sergeevich
  • Savchenko Andrej Yurevich
  • Ippolitov Sergej Viktorovich
  • Kryachkov Vyacheslav Nikolaevich
  • Resnyanskij Sergej Nikolaevich
RU2809719C1
METHOD FOR DIAGNOSING A COMPLEX OF ON-BOARD EQUIPMENT OF AIRCRAFT BASED ON MACHINE LEARNING AND A DEVICE FOR ITS IMPLEMENTATION 2023
  • Bukirev Aleksandr Sergeevich
  • Savchenko Andrej Yurevich
  • Ippolitov Sergej Viktorovich
  • Kryachkov Vyacheslav Nikolaevich
  • Resnyanskij Sergej Nikolaevich
RU2816667C1
METHOD FOR DIAGNOSING A COMPLEX OF ON-BOARD EQUIPMENT OF AIRCRAFT BASED ON UNSUPERVISED MACHINE LEARNING WITH AUTOMATIC DETERMINATION OF MODEL TRAINING PARAMETERS 2023
  • Bukirev Aleksandr Sergeevich
RU2818858C1

RU 2 824 522 C1

Authors

Vyshegorodtsev Kirill Evgenevich

Kuzmin Aleksandr Mikhajlovich

Dates

2024-08-08Published

2023-07-24Filed