Global ETD Search

461	Deep Learning Based Models for Cognitive Autonomy and Cybersecurity Intelligence in Autonomous Systems Ganapathy Mani (8840606) 21 June 2022 (has links) Cognitive autonomy of an autonomous system depends on its cyber module's ability to comprehend the actions and intent of the applications and services running on that system. The autonomous system should be able to accomplish this without or with limited human intervention. These mission-critical autonomous systems are often deployed in unpredictable and dynamic environments and are vulnerable to evasive cyberattacks. In particular, some of these cyberattacks are Advanced Persistent Threats where an attacker conducts reconnaissance for a long period time to ascertain system features, learn system defenses, and adapt to successfully execute the attack while evading detection. Thus an autonomous system's cognitive autonomy and cybersecurity intelligence depend on its capability to learn, classify applications (good and bad), predict the attacker's next steps, and remain operational to carryout the mission-critical tasks even under cyberattacks. In this dissertation, we propose novel learning and prediction models for enhancing cognitive autonomy and cybersecurity in autonomous systems. We develop (1) a model using deep learning along with a model selection framework that can classify benign and malicious operating contexts of a system based on performance counters, (2) a deep learning based natural language processing model that uses instruction sequences extracted from the memory to learn and profile the behavior of evasive malware, (3) a scalable deep learning based object detection model with data pre-processing assisted by fuzzy-based clustering, (4) fundamental guiding principles for cognitive autonomy using Artificial Intelligence (AI), (5) a model for privacy-preserving autonomous data analytics, and finally (6) a model for backup and replication based on combinatorial balanced incomplete block design in order to provide continuous availability in mission-critical systems. This research provides effective and computationally efficient deep learning based solutions for detecting evasive cyberattacks and increasing autonomy of a system from application-level to hardware-level. <br> Private policing and security services Knowledge representation and reasoning Pattern recognition System and network security Data mining and knowledge discovery Artificial Intelligence Cybersecurity Deep Learning Machine Learning Cryptomining Cryptojacking Natural Language Processing Malware Combinatorics Autonomous Systems Cognitive Autonomy Applied Computer Science Computer System Security Private Policing and Security Services Pattern Recognition and Data Mining
462	Eavesdropping Attacks on Modern-Day Connected Vehicles and Their Ramifications / Avlyssningsattacker på moderna uppkopplade bilar och deras följder Bakhshiyeva, Afruz, Berefelt, Gabriel January 2022 (has links) Vehicles today are becoming increasingly more connected. Most cars are equipped with Bluetooth, Wi-Fi and Wi-Fi hotspot capabilities and the ability to connect to the internet via a cellular modem. This increase in connectivity opens up new attack surfaces for hackers to exploit. This paper aims to study the security of three different cars, a Tesla Model 3 (2020), an MG Marvel R (2021) and a Volvo V90 (2017), in regards to three different eavesdropping attacks. The performed attacks were a port scan of the vehicles, a relay attack of the key fobs and a MITM attack. The study discovered some security risks and discrepancies between the vehicles, especially regarding the open ports and the relay attack. This hopefully promotes further discussion on the importance of cybersecurity in connected vehicles. / Bilar idag har blivit alltmer uppkopplade. Idag har de inte bara bluetooth och Wi-Fi funktionalitet utan vissa bilar har förmågan att kopplas till internet via ett mobilt bredband. Denna trend har visats ge bilar nya attackytor som hackare kan utnyttja. Målet med denna studie är att testa säkerheten hos tre olika bilar, Tesla Model 3 (2020), MG Marvel R (2021) och Volvo V90 (2017) med åtanke på tre olika avlyssningsattacker. De attackerna som studien valde var port-skanning på bilen, relä-attack på bilnycklarna och mannen-i-mitten attack. Studien hittar vissa säkerhetsrisker och skillnader mellan de olika bilarna särskilt vid reläattacken och port-skanningen som förhoppningsvis främjar en fortsatt diskussion om cybersäkerhetens vikt för säkrare uppkopplade bilar. Connected vehicle hacking pentest eavesdropping security Tesla Model 3 Volvo XC40 MG Marvel R automotive cybersecurity interception attacks passive attacks wireless attacks Wi-Fi attacks attack surface relay attack port scan man-in-the-middle attack Uppkopplade fordon hacking avlyssning säkerhet Tesla Model 3 Volvo XC40 MG Marvel R fordonscybersäkerhet avlyssningsattacker passiva attacker trådlösa attacker Wi-Fi-attacker attackyta relä-attack port-skanning mannen-i-mitten attack Computer Sciences Datavetenskap (datalogi)
463	Identifikace a charakterizace škodlivého chování v grafech chování / Identification and characterization of malicious behavior in behavioral graphs Varga, Adam January 2021 (has links) Za posledné roky je zaznamenaný nárast prác zahrňujúcich komplexnú detekciu malvéru. Pre potreby zachytenia správania je často vhodné pouziť formát grafov. To je prípad antivírusového programu Avast, ktorého behaviorálny štít deteguje škodlivé správanie a ukladá ich vo forme grafov. Keďže sa jedná o proprietárne riešenie a Avast antivirus pracuje s vlastnou sadou charakterizovaného správania bolo nutné navrhnúť vlastnú metódu detekcie, ktorá bude postavená nad týmito grafmi správania. Táto práca analyzuje grafy správania škodlivého softvéru zachytené behavioralnym štítom antivírusového programu Avast pre proces hlbšej detekcie škodlivého softvéru. Detekcia škodlivého správania sa začína analýzou a abstrakciou vzorcov z grafu správania. Izolované vzory môžu efektívnejšie identifikovať dynamicky sa meniaci malware. Grafy správania sú uložené v databáze grafov Neo4j a každý deň sú zachytené tisíce z nich. Cieľom tejto práce bolo navrhnúť algoritmus na identifikáciu správania škodlivého softvéru s dôrazom na rýchlosť skenovania a jasnosť identifikovaných vzorcov správania. Identifikácia škodlivého správania spočíva v nájdení najdôležitejších vlastností natrénovaných klasifikátorov a následnej extrakcie podgrafu pozostávajúceho iba z týchto dôležitých vlastností uzlov a vzťahov medzi nimi. Následne je navrhnuté pravidlo pre hodnotenie extrahovaného podgrafu. Diplomová práca prebehla v spolupráci so spoločnosťou Avast Software s.r.o.
464	Streamlining Certification Management with Automation and Certification Retrieval : System development using ABP Framework, Angular, and MongoDB / Effektivisering av certifikathantering med automatisering och certifikathämtning : Systemutveckling med ABP Framework, Angular och MongoDB Hassan, Nour Al Dine January 2024 (has links) This thesis examines the certification management challenge faced by Integrity360. The decentralized approach, characterized by manual processes and disparate data sources, leads to inefficient tracking of certification status and study progress. The main objective of this project was to construct a system that automates data retrieval, ensures a complete audit, and increases security and privacy. Leveraging the ASP.NET Boilerplate (ABP) framework, Angular, and MongoDB, an efficient and scalable system was designed, developed, and built based on DDD (domain-driven design) principles for a modular and maintainable architecture. The implemented system automates data retrieval from the Credly API, tracks exam information, manages exam vouchers, and implements a credible authentication system with role-based access control. With the time limitations behind the full-scale implementation of all the planned features, such as a dashboard with aggregated charts and automatic report generation, the platform significantly increases the efficiency and precision of employee certification management. Future work will include these advanced functionalities and integrations with external platforms to improve the system and increase its impact on operations in Integrity360. Certification Management Automation Certification Retrieval ABP Framework Angular MongoDB Credly API Exam Information Exam Vouchers Authentication Role-Based Access Control Data Retrieval Audit Security Privacy Efficiency Accuracy Scalability Maintainability Domain-Driven Design Software Development User Interface Data Encryption HTTPS Input Validation Identity Management Audit Logging Cybersecurity Education Training Employee Certification Study Progress Centralized Platform Data Integration Consolidated View Graphs Bar Charts Manual Data Entry Information Silos Decision Making Compliance Industry Standards Partner Levels Financial Penalties Reputation Damage Business Opportunities NoSQL Database Unstructured Data Semi-structured Data Software Architecture Layered Architecture Presentation Layer Application Layer Domain Layer Entities Value Objects Aggregates Repositories Domain Services Data Transfer Objects (DTOs) Business Logic Domain Semantics Modern Web Applications User Authentication Authorization Audit Logging Dynamic Web Applications Component-Based TypeScript Type Safety Code Quality Maintainability Active Community Charts Graphs Secure Submission LeptonX Lite Responsive Design Navigation Sidebar Menu Bar Tabs Table Attributes Properties Buttons Modal Dialogs Profile Settings System Admin Panel Account Management Permissions System Settings Certifikathantering Automatisering Certifikathämtning ABP Framework Angular MongoDB Credly API Examinformation Examenvouchers Autentisering Rollbaserad åtkomstkontroll Datahämtning Granskning Säkerhet Integritet Effektivitet Noggrannhet Skalbarhet Underhållbarhet Domändriven design Programvaruutveckling Användargränssnitt Datakryptering HTTPS Indata validering Identitetshantering Granskningsloggning Cybersäkerhet Utbildning Träning Medarbetarcertifiering Studie Framsteg Centraliserad plattform Dataintegration Konsoliderad vy Grafer Stapeldiagram Manuell datainmatning Informationssilos Beslutsfattande Efterlevnad Branschstandarder Partnernivåer Ekonomiska påföljder Ryktesskada Affärsmöjligheter NoSQL-databas Ostrukturerad data Semistrukturerad data Programvaruarkitektur Skiktad arkitektur Presentationslager Applikationslager Domänlager Entiteter Värdeobjekt Aggregat Repositories Domäntjänster Dataöverföringsobjekt (DTO) Affärslogik Domänsemantik Moderna webbapplikationer Användarautentisering Auktorisering Granskningsloggning Dynamiska webbapplikationer Komponentbaserad TypeScript Typsäkerhet Kodkvalitet Underhållbarhet Aktiv gemenskap Diagram Grafer Säker inlämning LeptonX Lite Responsiv design Navigering Sidofält Menyrad Flikar Tabell Attribut Egenskaper Knappar Modala dialogrutor Profilinställningar Systemadministratörspanel Kontohantering Behörigheter Systeminställningar Software Engineering Programvaruteknik

Page generated in 0.0477 seconds