ﻻ يوجد ملخص باللغة العربية
The last years of the 20 th century and the beginning of the 21 th mark the facilitation trend of our real life due to the big development and progress of the computers and other intelligent devices. Algorithms based on artificial intelligence are basically a part of the software. The transmitted information by Internet or LAN arises continuously and it is expected that the protection of the data has been ensured. The aim of the present paper is to reveal false names of users accounts as a result of hackers attacks. The probability a given account to be either false or actual is calculated using a novel approach combining machine learning analysis (especially clusters analysis) with chaos theory. The suspected account will be used as a pattern and by classification techniques clusters will be formed with a respective probability this name to be false. This investigation puts two main purposes: First, to determine if there exists a trend of appearance of the similar usernames, which arises during the creation of new accounts. Second, to detect the false usernames and to discriminate those from the real ones, independently of that if two types of accounts are generated with the same speed. These security systems are applied in different areas, where the security of the data in users accounts is strictly required. For example, they can be used in on-line voting for balloting, in studying the social opinion by inquiries, in protection of the information in different user accounts of given system etc.
The rise in the adoption of blockchain technology has led to increased illegal activities by cyber-criminals costing billions of dollars. Many machine learning algorithms are applied to detect such illegal behavior. These algorithms are often trained
We present a large-scale characterization of attacker activity across 111 real-world enterprise organizations. We develop a novel forensic technique for distinguishing between attacker activity and benign activity in compromised enterprise accounts t
We present a detailed discussion of our novel diagrammatic coupled cluster Monte Carlo (diagCCMC) [Scott et al. J. Phys. Chem. Lett. 2019, 10, 925]. The diagCCMC algorithm performs an imaginary-time propagation of the similarity-transformed coupled c
In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a carefully craft
The cybersecurity of smart grids has become one of key problems in developing reliable modern power and energy systems. This paper introduces a non-stationary adversarial cost with a variation constraint for smart grids and enables us to investigate