University of Lleida

About: University of Lleida is a education organization based out in Lleida, Spain. It is known for research contribution in the topics: Population & Pregnancy. The organization has 2939 authors who have published 5853 publications receiving 148417 citations. The organization is also known as: Escola Superior Politècnica & Universitat de Lleida.

Using convolutional neural networks for classification of malware represented as images

Abstract: The number of malicious files detected every year are counted by millions. One of the main reasons for these high volumes of different files is the fact that, in order to evade detection, malware authors add mutation. This means that malicious files belonging to the same family, with the same malicious behavior, are constantly modified or obfuscated using several techniques, in such a way that they look like different files. In order to be effective in analyzing and classifying such large amounts of files, we need to be able to categorize them into groups and identify their respective families on the basis of their behavior. In this paper, malicious software is visualized as gray scale images since its ability to capture minor changes while retaining the global structure helps to detect variations. Motivated by the visual similarity between malware samples of the same family, we propose a file agnostic deep learning approach for malware categorization to efficiently group malicious software into families based on a set of discriminant patterns extracted from their visualization as images. The suitability of our approach is evaluated against two benchmarks: the MalImg dataset and the Microsoft Malware Classification Challenge dataset. Experimental comparison demonstrates its superior performance with respect to state-of-the-art techniques.

Overexpression of the 67-kD laminin receptor correlates with tumour progression in human colorectal carcinoma.

Abstract: The high affinity 67-kD laminin receptor (67LR) is a cell surface protein whose expression is increased in a number of human carcinoma models. To date, 67LR expression in colorectal carcinomas has been examined in a small number of cases. 67LR expression has been immunohistochemically analysed in a large series of human colorectal neoplasms, using the MLuC5 monoclonal antibody. The study included 59 samples of non-neoplastic mucosa, 45 polyps (11 hyperplastic, 34 adenomas), 196 carcinomas, and lymph node metastases of 87 carcinomas. Epithelial cells of normal mucosa and hyperplastic polyps were negative or showed weak positivity in the paranuclear and apical areas of the cytoplasm. In adenomas and carcinomas, the staining was stronger, with a membranous or cytoplasmic pattern. The expression of 67LR correlated significantly with the progression from normal mucosa (22 per cent) to adenoma (44 per cent), carcinoma (61 per cent), and lymph node metastasis (75 per cent) (P < 0.0001). Expression of the laminin receptor showed a tendency to be more frequently positive in advanced stage (III+IV; 67 (III+IV; 67 per cent) when compared with early stage (I+II) carcinomas (54 per cent). The difference, however, was not statistically significant (P = 0.058). In addition, 14 out of 28 (50 per cent) primary carcinomas without 67LR expression became positive in lymph node metastases, while most (86 per cent) of the MLuC5-positive primary carcinomas were also immunoreactive in metastases. In conclusion, these results indicate that 67LR is up-regulated in the progression of human colorectal carcinomas and may play a role in the local and metastatic progression of these tumours.