This paper discusses a method for countering Sybil attacks in distributed systems based on the analysis of electromagnetic power maps of the temporal characteristics of network traffic. The key hypothesis is that multiple Sybil identifiers controlled by a single attacker node exhibit statistically significant correlation in their network activity patterns, which can be identified using a correlogram. A method for detecting Sybil attacks in wireless networks is proposed based on the analysis of correlograms of electromagnetic signal power maps. The method exploits the statistical properties of power profiles arising from the correlation of network activity of Sybil nodes controlled by a single attacker. A protection system architecture has been developed, including modules for network activity monitoring, correlogram calculation, clustering, and anomaly detection. A set of 10 correlogram parameters is introduced for attack identification, including profile variance, randomness and periodicity coefficients, spectral density, and correlation characteristics. Experimental testing on a millimeter-wave radar station demonstrated detection accuracy ranging from 83.2% to 97.4%. To improve the method's effectiveness, the use of deep neural networks after accumulating a sufficient amount of data is proposed. The proposed method enables the identification and denial of compromised identifiers, increasing the resilience of P2P networks, blockchain systems, and distributed ledgers.

Keywords: Sybil attack, distributed systems security, correlogram, network traffic analysis, time series, autocorrelation, anomaly detection

The purpose of the article: to determine the possibility of using file hash analysis using artificial neural networks to detect exploits in files. Research method: the search for exploits in files is carried out based on the analysis of Windows registry file hashes obtained by two hashing algorithms SHA-256 and SHA-512, using three types of artificial neural networks (direct propagation, recurrent, convolutional). The obtained result: the use of artificial neural networks in file hash analysis allows us to identify exploits or malicious records in files; the performance (accuracy) of artificial neural networks of direct propagation and with recurrent architecture are comparable to each other and are much more productive than convolutional neural networks; the longer the length of the file hash, the more reliably it is to identify an exploit in the file

Keywords: malware, exploit, neural networks, hashing, modeling