Anomaly Detection using system logs

Anomaly detection is a very important step in building a secure and trustworthy system. Manually it is daunting to analyze and detect failures and anomalies. In this paper, we proposed an approach that leverages the pattern matching capabilities of Convolution Neural Network (CNN) for anomaly detection in system logs. Features from log files are extracted using a windowing technique. Based on this feature, a one-dimensional image (1×n dimension) is generated where the pixel values of an image correlate with the features of the logs. On these images, the 1D Convolution operation is applied followed by max pooling. Followed by Convolution layers, a multi-layer feed-forward neural network is used as a classifier that learns to classify the logs as normal or abnormal from the representation created by the convolution layers. The model learns the variation in log pattern for normal and abnormal behavior. The proposed approach achieved improved accuracy compared to existing approaches for anomaly detection in Hadoop Distributed File System (HDFS) logs.

Impact sound prediction of finite floor structures with the modal transfer matrix method

The transfer matrix method (TMM) is commonly employed for wave propagation analysis in layered media of fluid, elastic and porous nature. Up to now it has been used extensively to analyze airborne sound transmission and sound absorption. Its use for impact sound transmission has been investigated to a limited extent, i.e. for thick homogeneous elastic plates of infinite extent and for specific receiver points. This contribution aims to broaden the scope such that the global impact sound, radiated by finite floor structures containing elastic, fluid and/or porous layers, can be analyzed in a more robust way than previously available in literature. A disadvantage of the conventional TMM is that only floors of infinite extent can be implemented. It is possible to remove this drawback using a spatial windowing technique. Furthermore, the modal behavior of the floor is approximately taken into account by projecting the impact force onto the mode shapes and only allowing for the propagation of those waves, corresponding to modal wavenumbers, in the structure. Predictions of the radiated sound power are made for various bare floors and floating floor systems of both infinite and finite extent.

The Effects of Egg Windowing on the Viability and Longevity of Gallus gallus Embryos in an Undergraduate Teaching Lab

The observation and manipulation of chicken embryos in ovo has been useful for understanding the development of vertebrates. However, the viability and longevity of the embryos are severely compromised even by simple manipulations to the egg shell. We have explored experimental protocols that promote the viability of embryos in ovo and ex ovo for use in an undergraduate teaching laboratory setting. Here, we demonstrate that a modified in ovo windowing technique increases survival time over an ex ovo method but with concomitant loss of spatial and temporal examination of chick embryo development.

Revealing and evaluating the influence of filters position in cascaded filter: application on the ECG de-noising performance disparity

In this paper, a new optimization on windowing technique based on finite impulse response (FIR) filters is proposed for revealing and evaluating the Influence of filters position in cascaded filter tested on the ECG signal de-noising. baseline wander (BLW), power line interference (PLI) and electromyography (EMG) noises are getting removed. The performance of the adopted method is evaluated on the PTB diagnostic database. Subsequently, the comparisons are based on signal to noise ratio (SNR) improvement and mean square error (MSE) minimization. Where the Rectangular, and Kaiser windows have been used for the more potent performances. The disparity average (DA) of SNR values is detected; in both Kaiser and Rectangular windows are assessed by ±0.38046dB and ±0.70278dB respectively, while the MSE values were constant. The excellent configuration or filters position (H-B-L) of the filtration system is selected according to high measurements of SNR and low MSE too, to de-noise the ECG signals. First of all, this applied approach has led to 31.30 dB SNR improvement with MSE minimization of 26. 43%. This means that there is a significant contribution to improving the field of filtration.

Data augmentation based malware detection using convolutional neural networks

Due to advancements in malware competencies, cyber-attacks have been broadly observed in the digital world. Cyber-attacks can hit an organization hard by causing several damages such as data breach, financial loss, and reputation loss. Some of the most prominent examples of ransomware attacks in history are WannaCry and Petya, which impacted companies’ finances throughout the globe. Both WannaCry and Petya caused operational processes inoperable by targeting critical infrastructure. It is quite impossible for anti-virus applications using traditional signature-based methods to detect this type of malware because they have different characteristics on each contaminated computer. The most important feature of this type of malware is that they change their contents using their mutation engines to create another hash representation of the executable file as they propagate from one computer to another. To overcome this method that attackers use to camouflage malware, we have created three-channel image files of malicious software. Attackers make different variants of the same software because they modify the contents of the malware. In the solution to this problem, we created variants of the images by applying data augmentation methods. This article aims to provide an image augmentation enhanced deep convolutional neural network (CNN) models for detecting malware families in a metamorphic malware environment. The main contributions of the article consist of three components, including image generation from malware samples, image augmentation, and the last one is classifying the malware families by using a CNN model. In the first component, the collected malware samples are converted into binary file to 3-channel images using the windowing technique. The second component of the system create the augmented version of the images, and the last part builds a classification model. This study uses five different deep CNN model for malware family detection. The results obtained by the classifier demonstrate accuracy up to 98%, which is quite satisfactory.