Social Engineering Attack Classifications on Social Media Using Deep燣earning

Aun, Yichiet; Gan, Ming-Lee; Wahab, Nur Haliza Abdul; Guan, Goh Hock

doi:10.32604/cmc.2023.032373

Cited by 6 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Para finalizar, el artículo en el Aun et al (2023) desarrollan un modelo de aprendizaje profundo RNN-LSTM capaz de identificar con alta precisión diferentes tipos de ataques de ingeniería social en publicaciones de redes sociales, como suplantación de identidad y phishing. Utilizando un pipeline de detección que analiza la fuente, el grafo social y el sentimiento de las publicaciones, el modelo logra clasificar estas amenazas con 0.84 de precisión y 0.81 de tasa de recuerdo, superando a otras técnicas de aprendizaje automático.…”

Section: Revista Multidisciplinar G-ner@ndo Isnn: 2806-5905unclassified

Estrategias innovadoras para mitigar la suplantación de identidad en redes sociales.

Macías Lara,

Bedoya Benavides,

Manchay Orbea

et al. 2024

Rev. Cient. Multi. G-nerando

View full text Add to dashboard Cite

La suplantación de identidad, también conocida como robo de identidad, constituye un desafío creciente en el entorno digital actual. A medida que nuestra vida cotidiana se integra cada vez más con la tecnología, es crucial abordar esta amenaza que puede tener repercusiones devastadoras para las víctimas, con el propósito de resaltar la importancia crítica de combatir la suplantación de identidad en la sociedad contemporánea. En este contexto, diversos estudios han propuesto estrategias para combatir este problema. Por ejemplo, Cheng et al. (2017) sugieren el desarrollo de sistemas de detección avanzados basados en inteligencia artificial, mientras que Goga et al. (2015) resaltan la importancia de integrar múltiples fuentes de información. Además, Khaled et al. (2018) proponen campañas de concientización y educación dirigidas a los usuarios para fortalecer su capacidad de protegerse. La implementación exitosa de estas estrategias promete un futuro más seguro y confiable para los usuarios en línea. Al mitigar los riesgos de suplantación de identidad y otros delitos cibernéticos, se fortalece la confianza en las plataformas en línea y se fomenta un entorno digital más inclusivo y accesible para todos. En última instancia, la colaboración entre individuos, empresas, gobiernos y profesionales de seguridad cibernética es fundamental para mantener la integridad y la confianza en un mundo digital en constante cambio. Este enfoque proactivo no solo protege la integridad de los usuarios, sino que también fortalece la confianza en las plataformas en línea, fomentando así un entorno digital más seguro y fiable para todos.

show abstract

Section: Revista Multidisciplinar G-ner@ndo Isnn: 2806-5905unclassified

Estrategias innovadoras para mitigar la suplantación de identidad en redes sociales.

Macías Lara,

Bedoya Benavides,

Manchay Orbea

et al. 2024

Rev. Cient. Multi. G-nerando

View full text Add to dashboard Cite

show abstract

“…The best performance is achieved with an ensemble approach for the identification and classification of crimerelated tweets that uses logistic regression (LR), SVMs, KNN, a decision tree (DT), and an RF classifier assigned the weights of 1, 2, 1, and 1, respectively, ensemble together via a soft weighted voting classifier along with a term frequency-inverse document frequency (TF-IDF) vectorizer with an accuracy of 96.2% on the testing dataset [41]. When compared to the ground truth labeled by network experts, an RNN-LSTM model that was trained to identify five different social engineering attacks (SEA) that may show signs of information gathering achieves classification precision and recall scores of 0.84 and 0.81, respectively [42].…”

Section: Related Workmentioning

confidence: 99%

A Multilayered Preprocessing Approach for Recognition and Classification of Malicious Social Network Messages

Čepulionytė,

Toldinas,

Lozinskis

2023

Electronics

View full text Add to dashboard Cite

The primary methods of communication in the modern world are social networks, which are rife with harmful messages that can injure both psychologically and financially. Most websites do not offer services that automatically delete or send malicious communications back to the sender for correction, or notify the sender of inaccuracies in the content of the messages. The deployment of such systems could make use of techniques for identifying and categorizing harmful messages. This paper suggests a novel multilayered preprocessing approach for the recognition and classification of malicious social network messages to limit negative impact, resulting in fewer toxic messages, scams, and aggressive comments in social media messages and commenting areas. As a result, less technical knowledge would be required to investigate the effects of harmful messages. The dataset was created using the regional Lithuanian language with four classes: aggressive, insulting, toxic, and malicious. Three machine learning algorithms were examined, five use cases of a multilayered preprocessing approach were suggested, and experiments were conducted to identify and classify harmful messages in the Lithuanian language.

show abstract

“…Once we had collected a sufficient amount of data, we developed a pipeline for data pre-processing that was specifically designed for the detection of social engineering attacks (SEAD). This pipeline allowed us to clean and prepare the data for analysis, which was essential for the development of ML model [21,22]. To identify posts that suggest a malicious intent to gather information, the SEADS model uses a variety of variables, including keyword matching, provenance filtering, and pattern recognition.…”

Section: Introductionmentioning

confidence: 99%

The Use of AI to Analyze Social Media Attacks for Predictive Analytics

Adekunle,

Lawrence,

Alabi

et al. 2024

AJOMIS

View full text Add to dashboard Cite

Social engineering, on the other hand, presents weaknesses that are difficult to directly quantify in penetration testing. The majority of expert social engineers utilize phishing and adware tactics to convince victims to provide information voluntarily. Social Engineering (SE) in social media has a similar structural layout to regular postings but has a malevolent intrinsic purpose. Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) was used to train a novel SE model to recognize covert SE threats in communications on social networks. The dataset includes a variety of posts, including text, images, and videos. It was compiled over a period of several months and was carefully curated to ensure that it is representative of the types of content that is typically posted on social media. First, by using domain heuristics, the social engineering assaults detection (SEAD) pipeline is intended to weed out social posts with malevolent intent. After tokenizing each social media post into sentences, each post is examined using a sentiment analyzer to determine whether it is a training data normal or an abnormality. Subsequently, an RNN-LSTM model is trained to detect five categories of social engineering assaults, some of which may involve information-gathering signals. Comparing the experimental findings to the ground truth labeled by network experts, the SEA model achieved 0.82 classification precision and 0.79 recall.

show abstract

Social Engineering Attack Classifications on Social Media Using Deep燣earning

Cited by 6 publications

References 26 publications

Estrategias innovadoras para mitigar la suplantación de identidad en redes sociales.

Estrategias innovadoras para mitigar la suplantación de identidad en redes sociales.

A Multilayered Preprocessing Approach for Recognition and Classification of Malicious Social Network Messages

The Use of AI to Analyze Social Media Attacks for Predictive Analytics

Contact Info

Product

Resources

About