TY - JOUR
AU1 - Zavadskii, E. V.
AU2 - Bulat, A. V.
AU3 - Gribkov, N. A.
AB - The modern trend of increasing labor productivity and business process efficiency entails the optimization of software development processes through the use of generative artificial intelligence models trained on various code bases and manual copying of code fragments. Given the growing number of registered vulnerabilities, methods for detecting clones of the software code are needed. A method for assessing the similarity of fragments of the program code of binary executable files, which is based on the representation of the code in the form of an FA-AAST tree and the apparatus of graph neural networks, is proposed. The results obtained during testing on open and closed source software demonstrate the correctness of the proposed method and higher accuracy compared to the solutions considered.
TI - Method of Searching for Clones of the Program Code in Binary Executive Files
JF - Automatic Control and Computer Sciences
DO - 10.3103/s0146411624700913
DA - 2024-12-01
UR - https://www.deepdyve.com/lp/springer-journals/method-of-searching-for-clones-of-the-program-code-in-binary-executive-BKIX00MLKz
SP - 1263
EP - 1270
VL - 58
IS - 8
DP - DeepDyve
ER -