Detection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective Optimization
Given the characteristics of IoT devices and the growing trend in their number, the security of these devices is critical. In particular, this paper will focus on Denial of Service (DoS) attacks, which seek to overload a service or device by using a machine to render the device inactive. Two machine...
- Autores:
-
Soto Parada, Erich Giusseppe
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2024
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/75191
- Acceso en línea:
- https://hdl.handle.net/1992/75191
- Palabra clave:
- DoS attacks
Machine Learning
Evolutionary algorithms
Inference times
Multi-objective optimization
Pseudo weights
Ingeniería
- Rights
- License
- Attribution-NonCommercial-NoDerivatives 4.0 International
| id |
UNIANDES2_b97151eb8261be93300b9f861df89394 |
|---|---|
| oai_identifier_str |
oai:repositorio.uniandes.edu.co:1992/75191 |
| network_acronym_str |
UNIANDES2 |
| network_name_str |
Séneca: repositorio Uniandes |
| repository_id_str |
|
| dc.title.eng.fl_str_mv |
Detection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective Optimization |
| title |
Detection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective Optimization |
| spellingShingle |
Detection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective Optimization DoS attacks Machine Learning Evolutionary algorithms Inference times Multi-objective optimization Pseudo weights Ingeniería |
| title_short |
Detection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective Optimization |
| title_full |
Detection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective Optimization |
| title_fullStr |
Detection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective Optimization |
| title_full_unstemmed |
Detection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective Optimization |
| title_sort |
Detection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective Optimization |
| dc.creator.fl_str_mv |
Soto Parada, Erich Giusseppe |
| dc.contributor.advisor.none.fl_str_mv |
Montoya Orozco, Germán Adolfo Lozano Garzon, Carlos Andres |
| dc.contributor.author.none.fl_str_mv |
Soto Parada, Erich Giusseppe |
| dc.contributor.researchgroup.none.fl_str_mv |
Facultad de Ingeniería::COMIT - Comunicaciones y Tecnología de Información |
| dc.subject.keyword.eng.fl_str_mv |
DoS attacks Machine Learning Evolutionary algorithms Inference times Multi-objective optimization Pseudo weights |
| topic |
DoS attacks Machine Learning Evolutionary algorithms Inference times Multi-objective optimization Pseudo weights Ingeniería |
| dc.subject.themes.spa.fl_str_mv |
Ingeniería |
| description |
Given the characteristics of IoT devices and the growing trend in their number, the security of these devices is critical. In particular, this paper will focus on Denial of Service (DoS) attacks, which seek to overload a service or device by using a machine to render the device inactive. Two machine learning models will be proposed: one from Random Forest, which has an F1 score of 0.99985 and an inference time of 0.457026 seconds for almost 500,000 records, and another from XGBoost, with an F1 score of 0.998989 and an inference time of 0.325767 seconds for the same 500,000 records. According to the methodologies explained, these models were the most suitable to meet the need for security in IoT devices. |
| publishDate |
2024 |
| dc.date.accessioned.none.fl_str_mv |
2024-10-29T13:12:42Z |
| dc.date.issued.none.fl_str_mv |
2024-10-28 |
| dc.type.none.fl_str_mv |
Trabajo de grado - Pregrado |
| dc.type.driver.none.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
| dc.type.coar.none.fl_str_mv |
http://purl.org/coar/resource_type/c_7a1f |
| dc.type.content.none.fl_str_mv |
Text |
| dc.type.redcol.none.fl_str_mv |
http://purl.org/redcol/resource_type/TP |
| format |
http://purl.org/coar/resource_type/c_7a1f |
| status_str |
acceptedVersion |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/1992/75191 |
| dc.identifier.instname.none.fl_str_mv |
instname:Universidad de los Andes |
| dc.identifier.reponame.none.fl_str_mv |
reponame:Repositorio Institucional Séneca |
| dc.identifier.repourl.none.fl_str_mv |
repourl:https://repositorio.uniandes.edu.co/ |
| url |
https://hdl.handle.net/1992/75191 |
| identifier_str_mv |
instname:Universidad de los Andes reponame:Repositorio Institucional Séneca repourl:https://repositorio.uniandes.edu.co/ |
| dc.language.iso.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.references.none.fl_str_mv |
[1] A. Srhir, T. Mazri, and M. Benbrahim, “Security in the iot: State-of-the-art, issues, solutions, and challenges,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 14, no. 5, pp. 65–75, 2023. [2] SonicWall, “Mid-year update 2023 sonicwall cyber threat report,” 2023, accessed: January 20, 2023. [Online]. Available: https://www.sonicwall.com [3] T. G. Nguyen, T. V. Phan, B. T. Nguyen, C. So-In, Z. A. Baig, and S. Sanguanpong, “Search: A collaborative and intelligent nids architecture for sdn-based cloud iot networks,” IEEE Access, vol. 7, pp. 107 678–107 694, 2019. [4] C. Kolias, G. Kambourakis, and A. Stavrou, “Ddos in the iot: Mirai and other botnets,” IEEE, vol. 50, no. 7, pp. 80–84, 2017. [5] R. Hat, “Red hat,” January 2023, available: https://www.redhat.com/es/topics/internet-of-things/what-is-iot. [6] J. Holdsworth and M. Scapicchio, “What is deep learning?” https://www.ibm.com/topics/deep-learning, 2024, updated: 17 June 2024. [7] B. Gupta and O. P. Badve, “Taxonomy of dos and ddos attacks and desirable defense mechanism in a cloud computing environment,” Neural Computing and Applications, vol. 28, pp. 3655–3682, 2017. [8] Cloudflare, “Cloudflare,” available: https://www.cloudflare.com/es-es/learning/ddos/glossary/denial-of-service/. [9] J. Murel and E. Kavlakoglu, “Ibm,” January 2024, available: https://www.ibm.com/topics/confusion-matrix. [10] J. D. Kelleher, B. Mac Namee, and A. D’Arcy, Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies. Cambridge, MA: MIT Press, 2015. [11] A. G´eron, Hands-On Machine Learning with Scikit-Learn, Keras, and Tensor-Flow, 3rd ed. Sebastopol, CA: O’Reilly Media, 2022. [12] IBM, “Ibm,” December 2023, available: https://www.ibm.com/topics/principal-component-analysis#:∼:text=IBM,of%20variables%2C%20called%20principal%20components. [13] H. Nelson, “Singular value decomposition: Image processing, natural language processing, and social media,” in Essential Math for AI. O’Reilly Media, 2023, ch. 6. [14] IBM, “Linear discriminant analysis,” 2023, accessed: 2024-10-10. [Online]. Available: https://www.ibm.com/topics/linear-discriminant-analysis [15] J. R. Turner and J. F. Thayer, “One-factor independent-groups analysis of variance,” in Introduction to Analysis of Variance. SAGE Publications, Inc., 2001, pp. 36–51. [Online]. Available: https://doi.org/10.4135/9781412984621 [16] N. Moustafa and J. Slay, “Unsw-nb15: A comprehensive data set for network intrusion detection systems (unsw-nb15 network data set),” in Military Communications and Information Systems Conference (MilCIS). IEEE, 2015, pp. 1–6. [17] ——, “The evaluation of network anomaly detection systems: Statistical analysis of the unsw-nb15 dataset and the comparison with the kdd99 dataset,” Information of the unsw-nb15 dataset and the comparison with the kdd99 dataset,” Information Security Journal: A Global Perspective, pp. 1–14, 2016. [18] N. Moustafa et al., “Novel geometric area analysis technique for anomaly detection using trapezoidal area estimation on large-scale networks,” IEEE Transactions on Big Data, 2017. [19] ——, “Big data analytics for intrusion detection system: Statistical decisionmaking using finite dirichlet mixture models,” in Data Analytics and Decision using finite dirichlet mixture models,” in Data Analytics and Decision Support for Cybersecurity. Springer, Cham, 2017, pp. 127–156. [20] M. Sarhan, S. Layeghy, N. Moustafa, and M. Portmann, “Netflow datasets for machine learning-based network intrusion detection systems,” in Big Data Technologies and Applications: 10th EAI International Conference, BDTA 2020, and 13th EAI International Conference on Wireless Internet, WiCON 2020. Springer Nature, 2020, p. 117. [21] N. Koroniotis, N. Moustafa, E. Sitnikova, and B. Turnbull, “Towards the development of realistic botnet dataset in the internet of things for network forensic analytics: Bot-iot dataset,” Future Generation Computer Systems, vol. 100, pp. 896–915, 2019. [22] J. G. Almaraz-Rivera, J. A. Perez-Diaz, J. A. Cantoral-Ceballos, J. F. Botero, and L. A. Trejo, “Latam-ddos-iot dataset,” 2022. [Online]. Available: Botero, and L. A. Trejo, “Latam-ddos-iot dataset,” 2022. [Online]. Available: https://dx.doi.org/10.21227/rwtj-dd43 [23] E. Neto, S. Dadkhah, R. Ferreira, A. Zohourian, R. Lu, and A. Ghorbani, “Ciciot2023: A real-time dataset and benchmark for large-scale attacks in iot environment,” Sensors, no. 5941, 2023. [24] K. Deb, Multi-Objective Optimization Using Evolutionary Algorithms. Chichester: John Wiley & Sons, 2001. [25] Ookla. (2024, September) Speedtest global index. Accessed: 2024-10-21. [Online]. Available: https://www.speedtest.net/global-index |
| dc.rights.en.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_f1cf |
| dc.rights.uri.none.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| dc.rights.coar.none.fl_str_mv |
http://purl.org/coar/access_right/c_f1cf |
| rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ http://purl.org/coar/access_right/c_f1cf http://purl.org/coar/access_right/c_f1cf |
| dc.format.extent.none.fl_str_mv |
34 páginas |
| dc.format.mimetype.none.fl_str_mv |
application/pdf |
| dc.publisher.none.fl_str_mv |
Universidad de los Andes |
| dc.publisher.program.none.fl_str_mv |
Ingeniería de Sistemas y Computación |
| dc.publisher.faculty.none.fl_str_mv |
Facultad de Ingeniería |
| dc.publisher.department.none.fl_str_mv |
Departamento de Ingeniería de Sistemas y Computación |
| publisher.none.fl_str_mv |
Universidad de los Andes |
| institution |
Universidad de los Andes |
| bitstream.url.fl_str_mv |
https://repositorio.uniandes.edu.co/bitstreams/0a649828-17f0-4ee0-bb17-c81aa9b4e9a9/download https://repositorio.uniandes.edu.co/bitstreams/df9c5998-bc8d-4085-8e32-8cc0fa004c60/download https://repositorio.uniandes.edu.co/bitstreams/8d48da6b-db88-4b58-b8bb-d8156ea3f78c/download https://repositorio.uniandes.edu.co/bitstreams/3c2c2a23-ead1-4ab5-9d96-7c0e009acbfd/download https://repositorio.uniandes.edu.co/bitstreams/a742d6b0-3664-4d15-9fc9-2089f2755816/download https://repositorio.uniandes.edu.co/bitstreams/4e7d951a-686a-49cb-addf-9fc3a1b15fb2/download https://repositorio.uniandes.edu.co/bitstreams/e8ae9116-9f7d-48b6-910c-3a434426d196/download https://repositorio.uniandes.edu.co/bitstreams/08de7592-8067-431d-b4e1-59f79366741a/download |
| bitstream.checksum.fl_str_mv |
e750f829237cd4093a15f7855dfe3493 9bac5d01661cacf7262386dd16c6b38b 4460e5956bc1d1639be9ae6146a50347 ae9e573a68e7f92501b6913cc846c39f 4cad7aa2312bbc552cf01ae0adb1ea4a 8a065e0aee5031f95d808e36de4bd0b0 d4084ea6f11494f46a0dd9b4ae5e2781 91fb58b544eccd1ac63e3918e283aad6 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio institucional Séneca |
| repository.mail.fl_str_mv |
adminrepositorio@uniandes.edu.co |
| _version_ |
1831927817468641280 |
| spelling |
Montoya Orozco, Germán Adolfovirtual::20113-1Lozano Garzon, Carlos Andresvirtual::23960-1Soto Parada, Erich GiusseppeFacultad de Ingeniería::COMIT - Comunicaciones y Tecnología de Información2024-10-29T13:12:42Z2024-10-28https://hdl.handle.net/1992/75191instname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/Given the characteristics of IoT devices and the growing trend in their number, the security of these devices is critical. In particular, this paper will focus on Denial of Service (DoS) attacks, which seek to overload a service or device by using a machine to render the device inactive. Two machine learning models will be proposed: one from Random Forest, which has an F1 score of 0.99985 and an inference time of 0.457026 seconds for almost 500,000 records, and another from XGBoost, with an F1 score of 0.998989 and an inference time of 0.325767 seconds for the same 500,000 records. According to the methodologies explained, these models were the most suitable to meet the need for security in IoT devices.Pregrado34 páginasapplication/pdfengUniversidad de los AndesIngeniería de Sistemas y ComputaciónFacultad de IngenieríaDepartamento de Ingeniería de Sistemas y ComputaciónAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/http://purl.org/coar/access_right/c_f1cf http://purl.org/coar/access_right/c_f1cfDetection of DoS Attacks in IoT Networks Using Machine Learning and Multi-Objective OptimizationTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/acceptedVersionhttp://purl.org/coar/resource_type/c_7a1fTexthttp://purl.org/redcol/resource_type/TPDoS attacksMachine LearningEvolutionary algorithmsInference timesMulti-objective optimizationPseudo weightsIngeniería[1] A. Srhir, T. Mazri, and M. Benbrahim, “Security in the iot: State-of-the-art, issues, solutions, and challenges,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 14, no. 5, pp. 65–75, 2023.[2] SonicWall, “Mid-year update 2023 sonicwall cyber threat report,” 2023, accessed: January 20, 2023. [Online]. Available: https://www.sonicwall.com[3] T. G. Nguyen, T. V. Phan, B. T. Nguyen, C. So-In, Z. A. Baig, and S. Sanguanpong, “Search: A collaborative and intelligent nids architecture for sdn-based cloud iot networks,” IEEE Access, vol. 7, pp. 107 678–107 694, 2019.[4] C. Kolias, G. Kambourakis, and A. Stavrou, “Ddos in the iot: Mirai and other botnets,” IEEE, vol. 50, no. 7, pp. 80–84, 2017.[5] R. Hat, “Red hat,” January 2023, available: https://www.redhat.com/es/topics/internet-of-things/what-is-iot.[6] J. Holdsworth and M. Scapicchio, “What is deep learning?” https://www.ibm.com/topics/deep-learning, 2024, updated: 17 June 2024.[7] B. Gupta and O. P. Badve, “Taxonomy of dos and ddos attacks and desirable defense mechanism in a cloud computing environment,” Neural Computing and Applications, vol. 28, pp. 3655–3682, 2017.[8] Cloudflare, “Cloudflare,” available: https://www.cloudflare.com/es-es/learning/ddos/glossary/denial-of-service/.[9] J. Murel and E. Kavlakoglu, “Ibm,” January 2024, available: https://www.ibm.com/topics/confusion-matrix.[10] J. D. Kelleher, B. Mac Namee, and A. D’Arcy, Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies. Cambridge, MA: MIT Press, 2015.[11] A. G´eron, Hands-On Machine Learning with Scikit-Learn, Keras, and Tensor-Flow, 3rd ed. Sebastopol, CA: O’Reilly Media, 2022.[12] IBM, “Ibm,” December 2023, available: https://www.ibm.com/topics/principal-component-analysis#:∼:text=IBM,of%20variables%2C%20called%20principal%20components.[13] H. Nelson, “Singular value decomposition: Image processing, natural language processing, and social media,” in Essential Math for AI. O’Reilly Media, 2023, ch. 6.[14] IBM, “Linear discriminant analysis,” 2023, accessed: 2024-10-10. [Online]. Available: https://www.ibm.com/topics/linear-discriminant-analysis[15] J. R. Turner and J. F. Thayer, “One-factor independent-groups analysis of variance,” in Introduction to Analysis of Variance. SAGE Publications, Inc., 2001, pp. 36–51. [Online]. Available: https://doi.org/10.4135/9781412984621[16] N. Moustafa and J. Slay, “Unsw-nb15: A comprehensive data set for network intrusion detection systems (unsw-nb15 network data set),” in Military Communications and Information Systems Conference (MilCIS). IEEE, 2015, pp. 1–6.[17] ——, “The evaluation of network anomaly detection systems: Statistical analysis of the unsw-nb15 dataset and the comparison with the kdd99 dataset,” Information of the unsw-nb15 dataset and the comparison with the kdd99 dataset,” Information Security Journal: A Global Perspective, pp. 1–14, 2016.[18] N. Moustafa et al., “Novel geometric area analysis technique for anomaly detection using trapezoidal area estimation on large-scale networks,” IEEE Transactions on Big Data, 2017.[19] ——, “Big data analytics for intrusion detection system: Statistical decisionmaking using finite dirichlet mixture models,” in Data Analytics and Decision using finite dirichlet mixture models,” in Data Analytics and Decision Support for Cybersecurity. Springer, Cham, 2017, pp. 127–156.[20] M. Sarhan, S. Layeghy, N. Moustafa, and M. Portmann, “Netflow datasets for machine learning-based network intrusion detection systems,” in Big Data Technologies and Applications: 10th EAI International Conference, BDTA 2020, and 13th EAI International Conference on Wireless Internet, WiCON 2020. Springer Nature, 2020, p. 117.[21] N. Koroniotis, N. Moustafa, E. Sitnikova, and B. Turnbull, “Towards the development of realistic botnet dataset in the internet of things for network forensic analytics: Bot-iot dataset,” Future Generation Computer Systems, vol. 100, pp. 896–915, 2019.[22] J. G. Almaraz-Rivera, J. A. Perez-Diaz, J. A. Cantoral-Ceballos, J. F. Botero, and L. A. Trejo, “Latam-ddos-iot dataset,” 2022. [Online]. Available: Botero, and L. A. Trejo, “Latam-ddos-iot dataset,” 2022. [Online]. Available: https://dx.doi.org/10.21227/rwtj-dd43[23] E. Neto, S. Dadkhah, R. Ferreira, A. Zohourian, R. Lu, and A. Ghorbani, “Ciciot2023: A real-time dataset and benchmark for large-scale attacks in iot environment,” Sensors, no. 5941, 2023.[24] K. Deb, Multi-Objective Optimization Using Evolutionary Algorithms. Chichester: John Wiley & Sons, 2001.[25] Ookla. (2024, September) Speedtest global index. Accessed: 2024-10-21. [Online]. Available: https://www.speedtest.net/global-index201818220Publicationhttps://scholar.google.es/citations?user=WRJlR-UAAAAJvirtual::23960-10000-0003-2920-6320virtual::23960-1https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000219541virtual::23960-1a197a9f7-96e5-47cb-a497-2ee4c9cdce71virtual::20113-1144aa5a0-592f-47a4-995b-a440d00b1658virtual::23960-1a197a9f7-96e5-47cb-a497-2ee4c9cdce71virtual::20113-1144aa5a0-592f-47a4-995b-a440d00b1658virtual::23960-1ORIGINALautorizacion tesis Erich Soto.pdfautorizacion tesis Erich Soto.pdfHIDEapplication/pdf232133https://repositorio.uniandes.edu.co/bitstreams/0a649828-17f0-4ee0-bb17-c81aa9b4e9a9/downloade750f829237cd4093a15f7855dfe3493MD52Detection of DoS attacks in IoT networks using Machine learning and multi-objective optimization.pdfDetection of DoS attacks in IoT networks using Machine learning and multi-objective optimization.pdfapplication/pdf434116https://repositorio.uniandes.edu.co/bitstreams/df9c5998-bc8d-4085-8e32-8cc0fa004c60/download9bac5d01661cacf7262386dd16c6b38bMD55CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.uniandes.edu.co/bitstreams/8d48da6b-db88-4b58-b8bb-d8156ea3f78c/download4460e5956bc1d1639be9ae6146a50347MD53LICENSElicense.txtlicense.txttext/plain; charset=utf-82535https://repositorio.uniandes.edu.co/bitstreams/3c2c2a23-ead1-4ab5-9d96-7c0e009acbfd/downloadae9e573a68e7f92501b6913cc846c39fMD54TEXTautorizacion tesis Erich Soto.pdf.txtautorizacion tesis Erich Soto.pdf.txtExtracted texttext/plain1555https://repositorio.uniandes.edu.co/bitstreams/a742d6b0-3664-4d15-9fc9-2089f2755816/download4cad7aa2312bbc552cf01ae0adb1ea4aMD56Detection of DoS attacks in IoT networks using Machine learning and multi-objective optimization.pdf.txtDetection of DoS attacks in IoT networks using Machine learning and multi-objective optimization.pdf.txtExtracted texttext/plain58239https://repositorio.uniandes.edu.co/bitstreams/4e7d951a-686a-49cb-addf-9fc3a1b15fb2/download8a065e0aee5031f95d808e36de4bd0b0MD58THUMBNAILautorizacion tesis Erich Soto.pdf.jpgautorizacion tesis Erich Soto.pdf.jpgGenerated Thumbnailimage/jpeg11446https://repositorio.uniandes.edu.co/bitstreams/e8ae9116-9f7d-48b6-910c-3a434426d196/downloadd4084ea6f11494f46a0dd9b4ae5e2781MD57Detection of DoS attacks in IoT networks using Machine learning and multi-objective optimization.pdf.jpgDetection of DoS attacks in IoT networks using Machine learning and multi-objective optimization.pdf.jpgGenerated Thumbnailimage/jpeg6890https://repositorio.uniandes.edu.co/bitstreams/08de7592-8067-431d-b4e1-59f79366741a/download91fb58b544eccd1ac63e3918e283aad6MD591992/75191oai:repositorio.uniandes.edu.co:1992/751912025-02-17 15:32:20.319http://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 Internationalrestrictedhttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.coPGgzPjxzdHJvbmc+RGVzY2FyZ28gZGUgUmVzcG9uc2FiaWxpZGFkIC0gTGljZW5jaWEgZGUgQXV0b3JpemFjacOzbjwvc3Ryb25nPjwvaDM+CjxwPjxzdHJvbmc+UG9yIGZhdm9yIGxlZXIgYXRlbnRhbWVudGUgZXN0ZSBkb2N1bWVudG8gcXVlIHBlcm1pdGUgYWwgUmVwb3NpdG9yaW8gSW5zdGl0dWNpb25hbCBTw6luZWNhIHJlcHJvZHVjaXIgeSBkaXN0cmlidWlyIGxvcyByZWN1cnNvcyBkZSBpbmZvcm1hY2nDs24gZGVwb3NpdGFkb3MgbWVkaWFudGUgbGEgYXV0b3JpemFjacOzbiBkZSBsb3Mgc2lndWllbnRlcyB0w6lybWlub3M6PC9zdHJvbmc+PC9wPgo8cD5Db25jZWRhIGxhIGxpY2VuY2lhIGRlIGRlcMOzc2l0byBlc3TDoW5kYXIgc2VsZWNjaW9uYW5kbyBsYSBvcGNpw7NuIDxzdHJvbmc+J0FjZXB0YXIgbG9zIHTDqXJtaW5vcyBhbnRlcmlvcm1lbnRlIGRlc2NyaXRvcyc8L3N0cm9uZz4geSBjb250aW51YXIgZWwgcHJvY2VzbyBkZSBlbnbDrW8gbWVkaWFudGUgZWwgYm90w7NuIDxzdHJvbmc+J1NpZ3VpZW50ZScuPC9zdHJvbmc+PC9wPgo8aHI+CjxwPllvLCBlbiBtaSBjYWxpZGFkIGRlIGF1dG9yIGRlbCB0cmFiYWpvIGRlIHRlc2lzLCBtb25vZ3JhZsOtYSBvIHRyYWJham8gZGUgZ3JhZG8sIGhhZ28gZW50cmVnYSBkZWwgZWplbXBsYXIgcmVzcGVjdGl2byB5IGRlIHN1cyBhbmV4b3MgZGUgc2VyIGVsIGNhc28sIGVuIGZvcm1hdG8gZGlnaXRhbCB5L28gZWxlY3Ryw7NuaWNvIHkgYXV0b3Jpem8gYSBsYSBVbml2ZXJzaWRhZCBkZSBsb3MgQW5kZXMgcGFyYSBxdWUgcmVhbGljZSBsYSBwdWJsaWNhY2nDs24gZW4gZWwgU2lzdGVtYSBkZSBCaWJsaW90ZWNhcyBvIGVuIGN1YWxxdWllciBvdHJvIHNpc3RlbWEgbyBiYXNlIGRlIGRhdG9zIHByb3BpbyBvIGFqZW5vIGEgbGEgVW5pdmVyc2lkYWQgeSBwYXJhIHF1ZSBlbiBsb3MgdMOpcm1pbm9zIGVzdGFibGVjaWRvcyBlbiBsYSBMZXkgMjMgZGUgMTk4MiwgTGV5IDQ0IGRlIDE5OTMsIERlY2lzacOzbiBBbmRpbmEgMzUxIGRlIDE5OTMsIERlY3JldG8gNDYwIGRlIDE5OTUgeSBkZW3DoXMgbm9ybWFzIGdlbmVyYWxlcyBzb2JyZSBsYSBtYXRlcmlhLCB1dGlsaWNlIGVuIHRvZGFzIHN1cyBmb3JtYXMsIGxvcyBkZXJlY2hvcyBwYXRyaW1vbmlhbGVzIGRlIHJlcHJvZHVjY2nDs24sIGNvbXVuaWNhY2nDs24gcMO6YmxpY2EsIHRyYW5zZm9ybWFjacOzbiB5IGRpc3RyaWJ1Y2nDs24gKGFscXVpbGVyLCBwcsOpc3RhbW8gcMO6YmxpY28gZSBpbXBvcnRhY2nDs24pIHF1ZSBtZSBjb3JyZXNwb25kZW4gY29tbyBjcmVhZG9yIGRlIGxhIG9icmEgb2JqZXRvIGRlbCBwcmVzZW50ZSBkb2N1bWVudG8uPC9wPgo8cD5MYSBwcmVzZW50ZSBhdXRvcml6YWNpw7NuIHNlIGVtaXRlIGVuIGNhbGlkYWQgZGUgYXV0b3IgZGUgbGEgb2JyYSBvYmpldG8gZGVsIHByZXNlbnRlIGRvY3VtZW50byB5IG5vIGNvcnJlc3BvbmRlIGEgY2VzacOzbiBkZSBkZXJlY2hvcywgc2lubyBhIGxhIGF1dG9yaXphY2nDs24gZGUgdXNvIGFjYWTDqW1pY28gZGUgY29uZm9ybWlkYWQgY29uIGxvIGFudGVyaW9ybWVudGUgc2XDsWFsYWRvLiBMYSBwcmVzZW50ZSBhdXRvcml6YWNpw7NuIHNlIGhhY2UgZXh0ZW5zaXZhIG5vIHNvbG8gYSBsYXMgZmFjdWx0YWRlcyB5IGRlcmVjaG9zIGRlIHVzbyBzb2JyZSBsYSBvYnJhIGVuIGZvcm1hdG8gbyBzb3BvcnRlIG1hdGVyaWFsLCBzaW5vIHRhbWJpw6luIHBhcmEgZm9ybWF0byBlbGVjdHLDs25pY28sIHkgZW4gZ2VuZXJhbCBwYXJhIGN1YWxxdWllciBmb3JtYXRvIGNvbm9jaWRvIG8gcG9yIGNvbm9jZXIuPC9wPgo8cD5FbCBhdXRvciwgbWFuaWZpZXN0YSBxdWUgbGEgb2JyYSBvYmpldG8gZGUgbGEgcHJlc2VudGUgYXV0b3JpemFjacOzbiBlcyBvcmlnaW5hbCB5IGxhIHJlYWxpesOzIHNpbiB2aW9sYXIgbyB1c3VycGFyIGRlcmVjaG9zIGRlIGF1dG9yIGRlIHRlcmNlcm9zLCBwb3IgbG8gdGFudG8sIGxhIG9icmEgZXMgZGUgc3UgZXhjbHVzaXZhIGF1dG9yw61hIHkgdGllbmUgbGEgdGl0dWxhcmlkYWQgc29icmUgbGEgbWlzbWEuPC9wPgo8cD5FbiBjYXNvIGRlIHByZXNlbnRhcnNlIGN1YWxxdWllciByZWNsYW1hY2nDs24gbyBhY2Npw7NuIHBvciBwYXJ0ZSBkZSB1biB0ZXJjZXJvIGVuIGN1YW50byBhIGxvcyBkZXJlY2hvcyBkZSBhdXRvciBzb2JyZSBsYSBvYnJhIGVuIGN1ZXN0acOzbiwgZWwgYXV0b3IgYXN1bWlyw6EgdG9kYSBsYSByZXNwb25zYWJpbGlkYWQsIHkgc2FsZHLDoSBkZSBkZWZlbnNhIGRlIGxvcyBkZXJlY2hvcyBhcXXDrSBhdXRvcml6YWRvcywgcGFyYSB0b2RvcyBsb3MgZWZlY3RvcyBsYSBVbml2ZXJzaWRhZCBhY3TDumEgY29tbyB1biB0ZXJjZXJvIGRlIGJ1ZW5hIGZlLjwvcD4KPHA+U2kgdGllbmUgYWxndW5hIGR1ZGEgc29icmUgbGEgbGljZW5jaWEsIHBvciBmYXZvciwgY29udGFjdGUgY29uIGVsIDxhIGhyZWY9Im1haWx0bzpiaWJsaW90ZWNhQHVuaWFuZGVzLmVkdS5jbyIgdGFyZ2V0PSJfYmxhbmsiPkFkbWluaXN0cmFkb3IgZGVsIFNpc3RlbWEuPC9hPjwvcD4K |