Dynamic Feature Dataset for Ransomware Detection Using Machine Learning Algorithms.

Ransomware-related cyber-attacks have been on the rise over the last decade, disturbing organizations considerably. Developing new and better ways to detect this type of malware is necessary. This research applies dynamic analysis and machine learning to identify the ever-evolving ransomware signatures using selected dynamic features. Since most of the attributes are shared by diverse ransomware-affected samples, our study can be used for detecting current and even new variants of the threat. This research has the following objectives: (1) Execute experiments with encryptor and locker ransomware combined with goodware to generate JSON files with dynamic parameters using a sandbox. (2) Analyze and select the most relevant and non-redundant dynamic features for identifying encryptor and locker ransomware from goodware. (3) Generate and make public a dynamic features dataset that includes these selected parameters for samples of different artifacts. (4) Apply the dynamic feature dataset to obtain models with machine learning algorithms. Five platforms, 20 ransomware, and 20 goodware artifacts were evaluated. The final feature dataset is composed of 2000 registers of 50 characteristics each. This dataset allows for a machine learning detection with a 10-fold cross-evaluation with an average accuracy superior to 0.99 for gradient boosted regression trees, random forest, and neural networks.

ECOG is as independent predictor of the response to chemotherapy, overall survival and progression-free survival in carcinoma of unknown primary site.

The aim of the present study was to determine whether age, gender, functional status, histology, tumor location, number of metastases, and levels of the tumor markers, lactate dehydrogenase (LDH) and albumin, are poor prognostic factors for the response to chemotherapy in patients with carcinoma of unknown primary site. A total of 149 patients diagnosed with carcinoma of unknown primary site that was histologically confirmed, and treated with chemotherapy in the Oncology Hospital, National Medical Center, 'Century XXI' IMSS, Mexico City, Mexico during the period between January 2002 to December 2009, were carefully selected for the present study. The analysis of 149 patients diagnosed with carcinoma of unknown primary site revealed that the liver was the organ with the highest frequency of metastases (33.5%). The objective response rates to chemotherapy were ~30.2%. Notably, ECOG was an important predictor of response to chemotherapy (P=0.008). The median progression-free survival was 7.1 months. Upon multivariate analysis, the Eastern Cooperative Oncology Group (ECOG) Scale of Performance Status was observed as an independent predictor of progression (P<0.0001). The median overall survival was 14.2 months. The ECOG was also an independent predictor of mortality (P<0.0001). In conclusion, the data from the present study have demonstrated that ECOG is an independent predictor of a poor response to chemotherapy, lower overall survival and progression-free survival in carcinoma of unknown primary site.

[Frequency of association of rheumatoid factor in patients with breast cancer]. / Frecuencia de asociación del factor reumatoide en pacientes con cáncer de mama.

AIMS: It has been reported that some patients with cancer present auto-immune phenomenon mediated by auto-antibodies, suggesting a relationship between auto-immunity and cancer. Our interest was to determine the frequency of association of rheumatoid factor and breast cancer. MATERIAL AND METHOD: Fifty patients were studied, 3 on stage 111 and 19 on stage IV. Rheumatoid factor was measured in all of them. Auto-antibodies were measured by ELISA. The clinical files of all the patients were reviewed to determine the presence of metastases (osseous, pulmonary, CNS and hepatic) as well as the histological type of the cancer to correlate the expression of the rheumatoid factor with the patients' clinical status. RESULTS: Four (12.9%) out of the 31 patients on stage 111 had positive rheumatoid factor, while 9 (47.3%) out of 19 patients on stage IV had positive rheumatoid factor. The mean age of the patients on stage 111 with positive rheumatoid factor was 48 years, while the mean age of the patients on stage IV with positive rheumatoid factor was 53 years. Patients on stage 111 with positive rheumatoid factor only had local-regional metastases while patients on stage IV with positive rheumatoid factor had distant metastases. The predominant histological type was adenocarcinoma. CONCLUSION: In this study it is shown that breast cancer on the most advanced stages have higher expression of rheumatoid factor, and more clinical derangement with higher levels of rheumatoid factor expression. The proposal of auto-antibodies as predictors of the severity of the cancer requires further studies on several types of cancer.