A5084352657- Biometric Identification and Security
- Imbalanced Data Classification Techniques
- Data Mining Algorithms and Applications
- Anomaly Detection Techniques and Applications
- Forensic and Genetic Research
- Machine Learning and Data Classification
- Network Security and Intrusion Detection
- User Authentication and Security Systems
- Forensic Fingerprint Detection Methods
- Dermatoglyphics and Human Traits
- Advanced Malware Detection Techniques
- Rough Sets and Fuzzy Logic
- Advanced Clustering Algorithms Research
- Complex Network Analysis Techniques
- Wood and Agarwood Research
- Neural Networks and Applications
- Digital and Cyber Forensics
- Adversarial Robustness in Machine Learning
- Explainable Artificial Intelligence (XAI)
- Face and Expression Recognition
- Spam and Phishing Detection
- Advanced Steganography and Watermarking Techniques
- Data Stream Mining Techniques
- Internet Traffic Analysis and Secure E-voting
- Data Visualization and Analytics
Tecnológico de Monterrey
2015-2021
National Institute of Astrophysics, Optics and Electronics
2011-2015
Universidad de Ciego de Ávila
2006-2012
The importance of understanding and explaining the associated classification results in utilization artificial intelligence (AI) many different practical applications (e.g., cyber security forensics) has contributed to trend moving away from black-box / opaque AI towards explainable (XAI). In this article, we propose first interpretable autoencoder based on decision trees, which is designed handle categorical data without need transform representation. Furthermore, our proposed provides a...
Improving fingerprint matching algorithms is an active and important research area in recognition. Algorithms based on minutia triplets, matcher family, present some drawbacks that impact their accuracy, such as dependency to the order of minutiae feature, insensitivity reflection directions relative sides triangle. To alleviate these drawbacks, we introduce this paper a novel algorithm, named M3gl. This algorithm contains three components: new feature representation containing...
Nowadays, the international scientific community of machine learning has an enormous campaign in favor creating understandable models instead black-box models. The main reason is that experts application area are showing reluctance due to cannot be understood by them, and consequently, their results difficult explained. In unsupervised problems, where have not labeled objects, obtaining explanation necessary because specialists need understand both applied model as well obtained for finding...
Latent fingerprint identification is essential in forensic science for linking suspects to crime scenes or, conversely, confirming a person's innocence. However, latent fingerprints often are partial prints with undesirable characteristics such as noise or distortion. Due these characteristics, identifying the physical details of fingerprint, known minutiae, complex task. Recent publications found that there minutiae that, when removed, increase matching score. We have defined this type...
The reach and influence of social networks over modern society its functioning have created new challenges opportunities to prevent the misuse or tampering such powerful tools interaction. Twitter, a networking service that specializes in online news information exchange involving billions users world-wide, has been infested by bots for several years. In this paper, we analyze both public private databases from literature bot detection on Twitter. We summarize their advantages,...
Most studies in masquerade detection focus mainly on the user action, ignoring object upon which that action is performed. This may yield limited models, since, for example, command execution (an action) usually ends up transformation of a file (the object). The overall goal this paper to prove paramount distinguishing from masquerade. With mind, we have developed new approach detection, called system navigation, and tested our ideas using Windows-Users Windows-Intruder simulations Logs Data...
DNS DDoS attacks may severely affect the operation of computer networks, prompting need for methods able to timely detect them, and then apply mitigation countermeasures. Visual models have been used an ongoing attack, but often demand continuous attention from IT staff. However, machine learning techniques could complement a visual model with further information on-time alerts that help officers give only when attack is in progress at its very early stage. In this paper, we present...
Latent palmprint identification is a crucial element for both law enforcement and integrated automated fingerprint systems because approximately 30% of the imprints found in crime scene originate from human's palms. To find person whom belongs to, forensic experts use that automatically compare found, called latent, against thousands potential palmprints. Identification rely on features obtained palmprint, different feature representations to include discriminative information. However,...