Identificación de ejemplos adversarios en modelos de Machine Learning que detectan malware para Android
| dc.contributor.advisor | Camargo Mendoza, Jorge Eliecer | spa |
| dc.contributor.author | Aldana Burgos, Leidy Marcela | spa |
| dc.contributor.referee | González Osorio, Fabio Augusto | spa |
| dc.contributor.referee | Niño Vásquez, Luis Fernando | spa |
| dc.contributor.researchgroup | Unsecurelab Cybersecurity Research Group | eng |
| dc.date.accessioned | 2026-01-21T19:41:09Z | |
| dc.date.available | 2026-01-21T19:41:09Z | |
| dc.date.issued | 2025-11-26 | |
| dc.description | ilustraciones, diagramas, fotografías | spa |
| dc.description.abstract | Este documento muestra un método computacional para identificar entradas adversarias en Machine Learning, enfocado en la detección de Malware para Android. En primer lugar, se creó un conjunto de datos de malware, con el cual se entrenaron cuatro modelos de machine learning, estos cuatro modelos son una red neuronal, un Autoencoder, SVM y regresión logística; todos ellos tienen el objetivo de aprender a clasificar aplicaciones para Android entre beningware o malware. En segundo lugar, se ejecutaron diez ataques adversarios de evasión contra cada uno de esos modelos de machine learning, los cuales son FGSM, BIM, CW (L2 y Linf), ZOO, HopSkip Jump, JSMA, Deepfool, PGD y Boundary Attack. La implementación de estos ataques permitió analizar la vulnerabilidad de estos modelos, debido a que logra alterar la clasificación que hace cada modelo. En tercer lugar, se propone un método sencillo para mitigar los efectos de dicha vulnerabilidad, el cual tiene el enfoque de detectar ejemplos adversarios previo a la entrada a cada modelo de machine learning; una vez detectados son excluidos y se evalúa de nuevo las métricas de rendimiento, como la evaluación cuantitativa de la capacidad para clasificar en cada modelo de machine learning. Finalmente, en los resultados se resalta la importancia de algunas características estáticas y dinámicas frecuentes en muestras de malware. (Texto tomado de la fuente). | spa |
| dc.description.abstract | This document presents a computational method for identifying adversarial inputs in Machine Learning, focused on Android malware detection. First, a malware dataset was created, with which four machine learning models were trained. These four models are a neural network, an autoencoder, an SVM, and logistic regression; all of them aim to learn how to classify Android applications as either beningware or malware. Second, ten adversarial evasion attacks were run against each of these machine learning models: FGSM, BIM, CW (L2 and Linf), ZOO, HopSkip Jump, JSMA, Deepfool, PGD, and Boundary Attack. The implementation of these attacks allowed us to analyze the vulnerability of these models, as it is able to alter the classification performed by each model. Third, a simple method is proposed to mitigate the effects of this vulnerability. This method focuses on detecting adversarial examples prior to entering each Machine Learning model. Once detected, they are excluded, and performance metrics are re-evaluated, such as a quantitative evaluation of the classification capacity of each Machine Learning model. Finally, the results highlight the importance of some common static and dynamic characteristics in malware samples. | eng |
| dc.description.degreelevel | Maestría | spa |
| dc.description.degreename | Magíster en Ingeniería de Sistemas y Computación | spa |
| dc.description.researcharea | Computación aplicada | spa |
| dc.format.extent | xii, 47 páginas | spa |
| dc.format.mimetype | application/pdf | |
| dc.identifier.instname | Universidad Nacional de Colombia | spa |
| dc.identifier.reponame | Repositorio Institucional Universidad Nacional de Colombia | spa |
| dc.identifier.repourl | https://repositorio.unal.edu.co/ | spa |
| dc.identifier.uri | https://repositorio.unal.edu.co/handle/unal/89285 | |
| dc.language.iso | spa | |
| dc.publisher | Universidad Nacional de Colombia | spa |
| dc.publisher.branch | Universidad Nacional de Colombia - Sede Bogotá | spa |
| dc.publisher.department | Departamento de Ingeniería de Sistemas e Industrial | spa |
| dc.publisher.faculty | Facultad de Ingeniería | spa |
| dc.publisher.place | Bogotá, Colombia | spa |
| dc.publisher.program | Bogotá - Ingeniería - Maestría en Ingeniería - Ingeniería de Sistemas y Computación | spa |
| dc.relation.references | M. Mendoza, Relato de un asesino. Editorial Planeta, jun. de 2021, pág. 288, Novela contemporánea, Epub 2, isbn: 978-958-42-9322-0 | |
| dc.relation.references | A. Panda, R. Chakravarty y S. Moulik, ‘‘Hand Gesture Recognition using Flex Sensor and Machine Learning Algorithms’’, mar. de 2021. doi: 10.1109/IECBES48179.2021.9398789 | |
| dc.relation.references | S. G. Selvaganapathy y S. Sadasivam, ‘‘Defense against adversarial malware using robust classifier: DAM-ROC’’, Sadhana, vol. 47, n.o 4, pág. 209, 2022, issn: 0973-7677. doi: 10.1007/s12046-022-019 80-6. dirección: https://doi.org/10.1007/s12046-022-01980-6 | |
| dc.relation.references | V. Zantedeschi, M. -I. Nicolae y A. Rawat, Efficient Defenses Against Adversarial Attacks, 2017. arXiv: 1707.06728 [cs.LG]. dirección: https://arxiv.org/abs/1707.06728 | |
| dc.relation.references | OWASP, OWASP Machine Learning Security Top Ten, Accedido el 17 de julio de 2025, 2023. dirección: https://owasp.org/www-project-machine-learning-security-top-10/ | |
| dc.relation.references | M. Chowdhury, A. Rahman y M. R. Islam, ‘‘Protecting data from malware threats using machine learning technique’’, jun. de 2017, págs. 1691-1694. doi: 10.1109/ICIEA.2017.8283111 | |
| dc.relation.references | H. Rathore, S. Agarwal, S. K. Sahay y M. Sewak, ‘‘Malware Detection Using Machine Learning and Deep Learning’’, en Big Data Analytics. Springer International Publishing, 2018, págs. 402-411, isbn: 9783030047801. doi: 10.1007/978-3-030-04780-1_28. dirección: http://dx.doi.org/10.1007/97 8-3-030-04780-1_28 | |
| dc.relation.references | R. Richardson y M. M. North, ‘‘Ransomware: Evolution, Mitigation and Prevention’’, International Management Review, vol. 13, n.o 1, págs. 10-21, 2017, Accessed: 2025-07-31. dirección: https://digit alcommons.kennesaw.edu/facpubs/4276 | |
| dc.relation.references | D. Gibert, C. Mateu y J. Planes, ‘‘The rise of machine learning for detection and classification of malware: Research developments, trends and challenges’’, Journal of Network and Computer Applications, vol. 153, pág. 102 526, 2020, issn: 1084-8045. doi: https://doi.org/10.1016/j.jnca.2019.102526. dirección: https://www.sciencedirect.com/science/article/pii/S1084804519303868 | |
| dc.relation.references | L. Chen, C.-Y. Yang, A. Paul y R. Sahita, Towards resilient machine learning for ransomware detection, 2019. arXiv: 1812.09400 [cs.LG]. dirección: https://arxiv.org/abs/1812.09400 | |
| dc.relation.references | G. D’Ambrosio y W. Li, ‘‘AdversarialDroid: A Deep Learning based Malware Detection Approach for Android System Against Adversarial Example Attacks’’, oct. de 2021, págs. 1-5. doi: 10.1109/URTC54 388.2021.9701615 | |
| dc.relation.references | H. Rathore, S. Sahay, P. Nikam y M. Sewak, ‘‘Robust Android Malware Detection System Against Adversarial Attacks Using Q-Learning’’, Information Systems Frontiers, vol. 23, págs. 1- 16, ago. de 2021. doi: 10.1007/s10796-020-10083-8 | |
| dc.relation.references | J. Zhang, C. Zhang, X. Liu, Y. Wang, W. Diao y S. Guo, ‘‘ShadowDroid: Practical Black-box Attack against ML-based Android Malware Detection’’, dic. de 2021, págs. 629 -636. doi: 10.1109/ICPADS533 94.2021.00084 | |
| dc.relation.references | J. Zhang, X. Xu, B. Han y col., Attacks Which Do Not Kill Training Make Adversarial Learning Stronger, 2020. arXiv: 2002.11242 [cs.LG]. dirección: https://arxiv.org/abs/2002.11242 | |
| dc.relation.references | Kaspersky, WannaCry Ransomware, https://www.kaspersky.es/resource-center/threats/rans omware-wannacry, Recuperado el 27 de noviembre de 2024, 2024 | |
| dc.relation.references | Y. Yilmaz, O. Cetin, B. Arief y J. Hernandez-Castro, ‘‘Investigating the impact of ransomware splash screens’’, Journal of Information Security and Applications, vol. 61, pág. 102 934, sep. de 2021. doi: 10.1016/j.jisa.2021.102934 | |
| dc.relation.references | L. Yuryna Connolly, D. S. Wall, M. Lang y B. Oddson, ‘‘An empirical study of ransomware attacks on organizations: an assessment of severity and salient factors affecting vulnerability’’, Journal of Cybersecurity, vol. 6, n.o 1, tyaa023, dic. de 2020, issn: 2057-2085. doi: 10.1093/cybsec/tyaa023. eprint: https://academic.oup.com/cybersecurity/article-pdf/6/1/tyaa023/35198032/tyaa02 3.pdf. dirección: https://doi.org/10.1093/cybsec/tyaa023 | |
| dc.relation.references | X. Qi, Y. Tang, H. Wang, T. Liu y J. Jing, ‘‘Adversarial Example Attacks Against Intelligent Malware Detection: A Survey’’, en 2022 4th International Conference on Applied Machine Learning (ICAML), 2022, págs. 1-7. doi: 10.1109/ICAML57167.2022.00068 | |
| dc.relation.references | L. Aldana y J. Camargo, ‘‘Adversarial Attacks in a Shallow Neural Network to Classify Android Malware’’, en Advances in Artificial Intelligence – IBERAMIA 2024, L. Correia, A. Rosá y F. Garijo, eds., Uruguay: Springer Cham, 2024, págs. 472-475 | |
| dc.relation.references | L. Aldana, Static and Dynamic Features with Adversarial Examples, https://www.kaggle.com/data sets/l7032681/static-and-dynamic-features-adv, 2024. dirección: https://www.kaggle.com/d atasets/l7032681/static-and-dynamic-features-adv | |
| dc.relation.references | L. Aldana, Dataset for Adversarial Machine Learning on Android Malware, https://github.com/le idy-m/dataset-advML, Accessed: 2025-07-30, 2024. dirección: https://github.com/leidy-m/datas et-advML | |
| dc.relation.references | L. Aldana, Adversarial Machine Learning on Android Malware Detection, https://github.com/lei dy-m/Adversarial-ML-Android-Malware, Accessed: 2025-07-30, 2024. dirección: https://github.c om/leidy-m/Adversarial-ML-Android-Malware | |
| dc.relation.references | N. Martins, J. M. Cruz, T. Cruz y P. Henriques Abreu, ‘‘Adversarial Machine Learning Applied to Intrusion and Malware Scenarios: A Systematic Review’’, IEEE Access, vol. 8, págs. 35 403 -35 419, 2020. doi: 10.1109/ACCESS.2020.2974752 | |
| dc.relation.references | K. Liu, S. Xu, G. Xu, M. Zhang, D. Sun y H. Liu, ‘‘A Review of Android Malware Detection Approaches Based on Machine Learning’’, IEEE Access, vol. 8, págs. 124 579-124 607, 2020. doi: 10.1109/ACCESS.2020.3006143 | |
| dc.relation.references | Z. Kong, J. Xue, Z. Liu, Y. Wang y W. Han, ‘‘MalDBA: Detection for Query-Based Malware Black-Box Adversarial Attacks’’, Electronics, vol. 12, n.o 7, 2023, issn: 2079-9292. doi: 10.3390/electronics12 071751. dirección: https://www.mdpi.com/2079-9292/12/7/1751 | |
| dc.relation.references | A. Rashid y J. Such, ‘‘StratDef: Strategic defense against adversarial attacks in ML-based malware detection’’, Computers & Security, vol. 134, pág. 103 459, 2023, issn: 0167-4048. doi: https://doi.or g/10.1016/j.cose.2023.103459. dirección: https://www.sciencedirect.com/science/article /pii/S0167404823003693 | |
| dc.relation.references | N. Wang, Y. Chen, Y. Hu, W. Lou e Y. T. Hou, ‘‘MANDA: On Adversarial Example Detection for Network Intrusion Detection System’’, en IEEE INFOCOM 2021 - IEEE Conference on Computer Communications, Vancouver, BC, Canada: IEEE Press, 2021, págs. 1 -10. doi: 10.1109/INFOCOM4298 1.2021.9488874. dirección: https://doi.org/10.1109/INFOCOM42981.2021.9488874 | |
| dc.relation.references | I. Rosenberg, A. Shabtai, Y. Elovici y L. Rokach, Defense Methods Against Adversarial Examples for Recurrent Neural Networks, 2019. arXiv: 1901.09963 [cs.CR]. dirección: https://arxiv.org/abs/1 901.09963 | |
| dc.relation.references | K. Grosse, P. Manoharan, N. Papernot, M. Backes y P. McDaniel, On the (Statistical) Detection of Adversarial Examples, 2017. arXiv: 1702.06280 [cs.CR]. dirección: https://arxiv.org/abs/1702 .06280 | |
| dc.relation.references | G. Android, Arquitectura de Android, https://developer.android.com/guide/platform, Último acceso: 11 de julio de 2025, 2025 | |
| dc.relation.references | D. Arp, E. Quiring, F. Pendlebury y col., ‘‘Dos and Don’ts of Machine Learning in Computer Security’’, en 31st USENIX Security Symposium (USENIX Security 22), Boston, MA, USA: USENIX Association, 2022. dirección: https://www.usenix.org/system/files/sec22-arp.pdf | |
| dc.relation.references | S. Nune, ‘‘Adversarial Attacks on Android Malware Detection and Classification’’, Master’s Project, San Jose State University, San Jose, California, Fall de 2022. doi: 10.31979/etd.gjhb-v87s. dirección: https://scholarworks.sjsu.edu/etd_projects/1196 | |
| dc.relation.references | S. Haykin, Neural Networks and Learning Machines, 3rd. Upper Saddle River, NJ, USA: Pearson, 2009 | |
| dc.relation.references | MathWorks, Autocodificadores (Autoencoders), Página web en español, access date 21-Aug-2025, MathWorks, 2025. dirección: https://la.mathworks.com/discovery/autoencoder.html | |
| dc.relation.references | scikit-learn developers, Support Vector Machines, Accessed: 2025-08-21, scikit-learn, 2025. dirección: https://scikit-learn.org/stable/modules/svm.html | |
| dc.relation.references | W. Villegas-Ch, A. Jaramillo-Alcázar y S. Luján-Mora, ‘‘Evaluating the Robustness of Deep Learning Models against Adversarial Attacks: An Analysis with FGSM, PGD and CW’’, Big Data and Cognitive Computing, vol. 8, n.o 1, 2024, issn: 2504-2289. doi: 10.3390/bdcc8010008. dirección: https://www .mdpi.com/2504-2289/8/1/8 | |
| dc.relation.references | I. H. Sarker, ‘‘Multi-aspects AI-based modeling and adversarial learning for cybersecurity intelligence and robustness: A comprehensive overview’’, SECURITY AND PRIVACY, vol. 6, n.o 5, e295, 2023. doi: https://doi.org/10.1002/spy2.295. eprint: https://onlinelibrary.wiley.com/doi/pdf /10.1002/spy2.295. dirección: https://onlinelibrary.wiley.com/doi/abs/10.1002/spy2.295 | |
| dc.relation.references | I. J. Goodfellow, J. Shlens y C. Szegedy, Explaining and Harnessing Adversarial Examples, 2015. arXiv: 1412.6572 [stat.ML]. dirección: https://arxiv.org/abs/1412.6572 | |
| dc.relation.references | TensorFlow Authors, Fast Gradient Sign Method, https://www.tensorflow.org/tutorials/gener ative/adversarial_fgsm, Accessed: 2025-08-03, 2024 | |
| dc.relation.references | D. Irigaray y C. Serena, ‘‘Ataques adversarios en sistemas de reconocimiento visual’’, Tutores: Dr. Mauricio Delbracio, Dr. José Lezama, Dr. Guillermo Moncecchi, Proyecto de Grado, Universidad de la República, Facultad de Ingeniería, Montevideo, Uruguay, dic. de 2019. dirección: https://www.fing .edu.uy/inco/grupos/pln/prygrado/informe_pgattack.pdf | |
| dc.relation.references | M. Intelligence y D. Learning, Deepfool: a simple and accurate method to fool deep neural networks, Video en YouTube, Accedido el 24 de agosto de 2025, abr. de 2022. dirección: https://www.youtube .com/watch?v=wSYbf_b3N14 | |
| dc.relation.references | S. - M. Moosavi-Dezfooli, A. Fawzi y P. Frossard, DeepFool: a simple and accurate method to fool deep neural networks, 2016. arXiv: 1511.04599 [cs.LG]. dirección: https://arxiv.org/abs/1511.04599 | |
| dc.relation.references | F. Wu, R. Gazo, E. Haviarova y B. Benes, Efficient Project Gradient Descent for Ensemble Adversarial Attack, 2019. arXiv: 1906.03333 [cs.LG]. dirección: https://arxiv.org/abs/1906.03333 | |
| dc.relation.references | T. Combey, A. Loison, M. Faucher y H. Hajri, Probabilistic Jacobian-based Saliency Maps Attacks, 2020. arXiv: 2007.06032 [cs.CV]. dirección: https://arxiv.org/abs/2007.06032 | |
| dc.relation.references | N. Carlini y D. Wagner, Towards Evaluating the Robustness of Neural Networks, 2017. arXiv: 1608.0 4644 [cs.CR]. dirección: https://arxiv.org/abs/1608.04644 | |
| dc.relation.references | P. -Y. Chen, H. Zhang, Y. Sharma, J. Yi y C. -J. Hsieh, ‘‘ZOO: Zeroth Order Optimization Based Black- box Attacks to Deep Neural Networks without Training Substitute Models’’, en Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, ép. CCS ’17, ACM, nov. de 2017, págs. 15-26. doi: 10.1145/3128572.3140448. dirección: http://dx.doi.org/10.1145/3128572.3140448 | |
| dc.relation.references | W. Brendel, J. Rauber y M. Bethge, Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models, 2018. arXiv: 1712.04248 [stat.ML]. dirección: https://arxiv .org/abs/1712.04248 | |
| dc.relation.references | J. Chen, M. I. Jordan y M. J. Wainwright, HopSkipJumpAttack: A Query-Efficient Decision-Based Attack, 2020. arXiv: 1904.02144 [cs.LG]. dirección: https://arxiv.org/abs/1904.02144 | |
| dc.relation.references | D. Arp, M. Spreitzenbarth, M. Hübner, H. Gascon y K. Rieck, ‘‘DREBIN: Effective and Explainable Detection of Android Malware in Your Pocket’’, feb. de 2014. doi: 10.14722/ndss.2014.23247 | |
| dc.relation.references | M. Spreitzenbarth, F. Freiling, F. Echtler, T. Schreck y J. Hoffmann, ‘‘Mobile-sandbox: Having a deeper look into Android applications’’, mar. de 2013, págs. 1808-1815. doi: 10.1145/2480362.2480701 | |
| dc.relation.references | A. Martín García, R. Lara-Cabrera y D. Camacho, ‘‘A new tool for static and dynamic Android malware analysis’’, págs. 509-516, sep. de 2018. doi: 10.1142/9789813273238_0066 | |
| dc.relation.references | A. Martín García, R. Lara-Cabrera y D. Camacho, ‘‘Android malware detection through hybrid features fusion and ensemble classifiers: The AndroPyTool framework and the OmniDroid dataset’’, Information Fusion, vol. 52, dic. de 2018. doi: 10.1016/j.inffus.2018.12.006 | |
| dc.relation.references | N. V. Chawla, K. W. Bowyer, L. O. Hall y W. P. Kegelmeyer, ‘‘SMOTE: Synthetic Minority Over- sampling Technique’’, Journal of Artificial Intelligence Research, vol. 16, págs. 321 -357, jun. de 2002, issn: 1076-9757. doi: 10.1613/jair.953. dirección: http://dx.doi.org/10.1613/jair.953 | |
| dc.relation.references | X. Wang, L. Zhang, K. Zhao, X. Ding y M. Yu, ‘‘MFDroid: A Stacking Ensemble Learning Framework for Android Malware Detection’’, Sensors, vol. 22, n.o 7, 2022, issn: 1424-8220. doi: 10.3390/s22072 597. dirección: https://www.mdpi.com/1424-8220/22/7/2597 | |
| dc.relation.references | C. C. U. López, J. S. D. Villarreal, A. F. P. Belalcazar, A. N. Cadavid y J. G. D. Cely, ‘‘Features to Detect Android Malware’’, en 2018 IEEE Colombian Conference on Communications and Computing (COLCOM), 2018, págs. 1-6. doi: 10.1109/ColComCon.2018.8466715 | |
| dc.relation.references | V. Kouliaridis, G. Kambourakis y T. Peng, ‘‘Feature Importance in Android Malware Detection’’, dic. de 2020. doi: 10.1109/TrustCom50675.2020.00195 | |
| dc.relation.references | J. Park, M. Kang, S.-j. Cho, H. Han y K. Suh, ‘‘Analysis of Permission Selection Techniques in Machine Learning-based Malicious App Detection’’, en 2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), 2020, págs. 92 - 99. doi: 10.1109/AIKE48582.2020.0 0021 | |
| dc.relation.references | Q. E. A. Ratul, N. Chowdhury, H. Soliman, M. S. Chaity y A. Haque, ‘‘Android Malware Detection in Large Dataset: Smart Approach’’, en feb. de 2020, págs. 800-814, isbn: 978-3-030-39444-8. doi: 10.1007/978-3-030-39445-5_58 | |
| dc.relation.references | A. Banik y J. P. Singh, ‘‘Android Malware Detection by Correlated Real Permission Couples Using FP Growth Algorithm and Neural Networks’’, IEEE Access, vol. 11, págs. 124 996 -125 010, 2023. doi: 10.1109/ACCESS.2023.3323845 | |
| dc.relation.references | X. Jiang, B. Mao, J. Guan y X. Huang, ‘‘Android Malware Detection Using Fine-Grained Features’’, Scientific Programming, vol. 2020, n.o 1, pág. 5 190 138, 2020. doi: https://doi.org/10.1155/2020 /5190138. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1155/2020/5190138. dirección: https://onlinelibrary.wiley.com/doi/abs/10.1155/2020/5190138 | |
| dc.relation.references | Y. Z. Xuxian Jiang, Android Malware. New York: Springer New York, NY, 2013, isbn: 978-1-4614- 7394-7. doi: 10.1007/978-1-4614-7394-7. dirección: https://springerlink.unalproxy.elogim .com/book/10.1007/978-1-4614-7394-7 | |
| dc.relation.references | Shashwatwork, Android Malware Dataset for Machine Learning, https://www.kaggle.com/dataset s/shashwatwork/android-malware-dataset-for-machine-learning, Accedido el 2 de septiembre de 2025, 2025 | |
| dc.relation.references | Google, Cursor (android.database) — Android Developers, https://developer.android.com/refer ence/android/database/Cursor, Accedido el 2 de septiembre de 2025, 2025 | |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | |
| dc.rights.license | Reconocimiento 4.0 Internacional | |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
| dc.subject.ddc | 000 - Ciencias de la computación, información y obras generales::005 - Programación, programas, datos de computación | spa |
| dc.subject.proposal | Adversario | spa |
| dc.subject.proposal | Red neuronal | spa |
| dc.subject.proposal | Regresión logística | spa |
| dc.subject.proposal | Malware | eng |
| dc.subject.proposal | Autoencoder | eng |
| dc.subject.proposal | Android | eng |
| dc.subject.proposal | Machine Learning | eng |
| dc.subject.proposal | SVM | eng |
| dc.subject.proposal | Adversarial | eng |
| dc.subject.proposal | Neural network | eng |
| dc.subject.proposal | Logistic regression | eng |
| dc.subject.unesco | Inteligencia artificial | spa |
| dc.subject.unesco | Artificial intelligence | eng |
| dc.subject.unesco | malware | spa |
| dc.subject.unesco | malware | eng |
| dc.subject.unesco | Seguridad de los datos | spa |
| dc.subject.unesco | data security | eng |
| dc.title | Identificación de ejemplos adversarios en modelos de Machine Learning que detectan malware para Android | spa |
| dc.title.translated | Identifying adversarial examples in Machine Learning models that detect malware for Android | eng |
| dc.type | Trabajo de grado - Maestría | spa |
| dc.type.coar | http://purl.org/coar/resource_type/c_bdcc | |
| dc.type.coarversion | http://purl.org/coar/version/c_ab4af688f83e57aa | |
| dc.type.content | Text | |
| dc.type.driver | info:eu-repo/semantics/masterThesis | |
| dc.type.redcol | http://purl.org/redcol/resource_type/TM | |
| dc.type.version | info:eu-repo/semantics/acceptedVersion | |
| dcterms.audience.professionaldevelopment | Público general | spa |
| oaire.accessrights | http://purl.org/coar/access_right/c_abf2 |
Archivos
Bloque original
1 - 1 de 1
Cargando...
- Nombre:
- iden.pdf
- Tamaño:
- 1.15 MB
- Formato:
- Adobe Portable Document Format
- Descripción:
- Tesis de Maestría en Ingeniería - Ingeniería de Sistemas y Computación
Bloque de licencias
1 - 1 de 1
Cargando...
- Nombre:
- license.txt
- Tamaño:
- 5.74 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción:

