Rocío Alaiz-Rodríguez

Phishing attacks pose a significant cybersecurity threat, evolving rapidly to bypass detection mechanisms and exploit human vulnerabilities. This paper introduces PhishKey to address the challenges of adaptability, robustness, and efficiency. PhishKey is a novel phishing detection method using automatic feature extraction from hybrid sources. PhishKey combines character-level processing with Convolutional Neural Networks (CNN) for URL classification, and a Centroid-Based Key Component Phishing Extractor (CAPE) for HTML content at the word level. CAPE reduces noise and ensures complete sample processing avoiding crop operations on the input data. The predictions from both modules are integrated using a soft-voting ensemble to achieve more accurate and reliable classifications. Experimental evaluations on four state-of-the-art datasets demonstrate the effectiveness of PhishKey. It achieves up to 98.70% F1 Score and shows strong resistance to adversarial manipulations such as injection attacks with minimal performance degradation.

In this work we propose a new online, low cost and fast approach based on computer vision and machine learning to determine whether cutting tools used in edge profile milling processes are serviceable or disposable based on their wear level. We created a new dataset of 254 images of edge profile cutting heads which is, to the best of our knowledge, the first publicly available dataset with enough quality for this purpose. All the inserts were segmented and their cutting edges were cropped, obtaining 577 images of cutting edges: 301 functional and 276 disposable. The proposed method is based on (1) dividing the cutting edge image in different regions, called Wear Patches (WP), (2) characterising each one as worn or serviceable using texture descriptors based on different variants of Local Binary Patterns (LBP) and (3) determine, based on the state of these WP, if the cutting edge (and, therefore, the tool) is serviceable or disposable. We proposed and assessed five different patch division configurations. The individual WP were classified by a Support Vector Machine (SVM) with an intersection kernel. The best patch division configuration and texture descriptor for the WP achieves an accuracy of 90.26% in the detection of the disposable cutting edges. These results show a very promising opportunity for automatic wear monitoring in edge profile milling processes.

In this paper, we propose Ranksum, an approach for extractive text summarization of single documents based on the rank fusion of four multi-dimensional sentence features extracted for each sentence: topic information, semantic content, significant keywords, and position. The Ranksum obtains the sentence saliency rankings corresponding to each feature in an unsupervised way followed by the weighted fusion of the four scores to rank the sentences according to their significance. The scores are generated in completely unsupervised way, and a labeled document set is required to learn the fusion weights. Since we found that the fusion weights can generalize to other datasets, we consider the Ranksum as an unsupervised approach. To determine topic rank, we employ probabilistic topic models whereas semantic information is captured using sentence embeddings. To derive rankings using sentence embeddings, we utilize Siamese networks to produce abstractive sentence representation and then we formulate a novel strategy to arrange them in their order of importance. A graph-based strategy is applied to find the significant keywords and related sentence rankings in the document. We also formulate a sentence novelty measure based on bigrams, trigrams, and sentence embeddings to eliminate redundant sentences from the summary. The ranks of all the sentences computed for each feature are finally fused to get the final score for each sentence in the document. We evaluate our approach on publicly available summarization datasets CNN/DailyMail and DUC 2002. Experimental results show that our approach outperforms other existing state-of-the-art summarization methods.

Feature selection is a key step when dealing with high dimensional data. In particular, these techniques simplify the process of knowledge discovery from the data by selecting the most relevant features out of the noisy, redundant and irrelevant features. A problem that arises in many of these practical applications is that the outcome of the feature selection algorithm is not stable. Thus, small variations in the data may yield very different feature rankings. Assessing the stability of these methods becomes an important issue in the previously mentioned situations. We propose an information theoretic approach based on the Jensen Shannon divergence to quantify this robustness. Unlike other stability measures, this metric is suitable for different algorithm outcomes: full ranked lists, feature subsets as well as the lesser studied partial ranked lists. This generalized metric quantifies the difference among a whole set of lists with the same size, following a probabilistic approach and being able to give more importance to the disagreements that appear at the top of the list. Moreover, it possesses desirable properties including correction for change, upper lower bounds and conditions for a deterministic selection. We illustrate the use of this stability metric with data generated in a fully controlled way and compare it with popular metrics including the Spearmans rank correlation and the Kunchevas index on feature ranking and selection outcomes, respectively. Additionally, experimental validation of the proposed approach is carried out on a real-world problem of food quality assessment showing its potential to quantify stability from different perspectives.

Background and objective Risk prediction models aim at identifying people at higher risk of developing a target disease. Feature selection is particularly important to improve the prediction model performance avoiding overfitting and to identify the leading cancer risk (and protective) factors. Assessing the stability of feature selection/ranking algorithms becomes an important issue when the aim is to analyze the features with more prediction power. Methods This work is focused on colorectal cancer, assessing several feature ranking algorithms in terms of performance for a set of risk prediction models (Neural Networks, Support Vector Machines (SVM), Logistic Regression, k-Nearest Neighbors and Boosted Trees). Additionally, their robustness is evaluated following a conventional approach with scalar stability metrics and a visual approach proposed in this work to study both similarity among feature ranking techniques as well as their individual stability. A comparative analysis is carried out between the most relevant features found out in this study and features provided by the experts according to the state-of-the-art knowledge. Results The two best performance results in terms of Area Under the ROC Curve (AUC) are achieved with a SVM classifier using the top-41 features selected by the SVM wrapper approach (AUC=0.693) and Logistic Regression with the top-40 features selected by the Pearson (AUC=0.689). Experiments showed that performing feature selection contributes to classification performance with a 3.9% and 1.9% improvement in AUC for the SVM and Logistic Regression classifier, respectively, with respect to the results using the full feature set. The visual approach proposed in this work allows to see that the Neural Network-based wrapper ranking is the most unstable while the Random Forest is the most stable.

Recent studies have shown that phishers are using phishing kits to deploy phishing attacks faster, easier and more massive. Detecting phishing kits in deployed websites might help to detect phishing campaigns earlier. To the best of our knowledge, there are no datasets providing a set of phishing kits that are used in websites that were attacked by phishing. In this work, we propose PhiKitA, a novel dataset that contains phishing kits and also phishing websites generated using these kits. We have applied MD5 hashes, fingerprints, and graph representation DOM algorithms to obtain baseline results in PhiKitA in three experiments: familiarity analysis of phishing kit samples, phishing website detection and identifying the source of a phishing website. In the familiarity analysis, we find evidence of different types of phishing kits and a small phishing campaign. In the binary classification problem for phishing detection, the graph representation algorithm achieved an accuracy of 92.50%, showing that the phishing kit data contain useful information to classify phishing. Finally, the MD5 hash representation obtained a 39.54% F1 score, which means that this algorithm does not extract enough information to distinguish phishing websites and their phishing kit sources properly.

Beef derived from grass-fed cattle is a specific quality criterion. The effect of grass silage intake on quality characteristics, i.e., fatty acids, fat-soluble vitamins, and lipid-derived volatile composition of intramuscular and perirenal fat from fattening bull weaners were studied. Visible (VIS) and near-infrared (NIR) spectra were also obtained from perirenal fat. Perirenal fat analysis was performed for feeding differentiation purposes. A total of 22 Tudanca breed 11-month-aged bulls were finished on three different diets: grass silage and a commercial concentrate ad libitum (GS-AC), grass silage ad libitum and the commercial concentrate restricted to half of the intake of the GS-AC group (GS-LC), and barley straw and concentrate ad libitum (Str-AC). Feeding had a significant effect (p < 0.05) on γ-linolenic acid and the ratio n-6/n-3 fatty acids. Furthermore, β-carotene content was greater in beef from silage groups than in the Str-AC group. Feeding also affected the perirenal fat composition. Beef from silage-fed bulls and straw-fed bulls could be differentiated by fatty acid percentages, especially 18:0, t-18:1, and c9-18:1, β-carotene content, b* colour value, and carotenoid colour index. However, the VIS or NIR spectra data showed poor differentiating performance, and the volatile composition did not have appreciable differentiation power.