Load balancing is currently considered as a candidate solution to tackle the emerging problem of increasing bandwidth demand in intra-datacenter networks. Furthermore, because a short disruption of data transfer would corrupt the result of a long procedure of computation, fast failure management mechanisms are considered as integral part of current datacenters. In this paper, we propose a method which uses active probing to detect and manage failures in an OpenFlow based datacenter network exploiting load balancing among equal cost multiple paths. The proposed method is scalable and effective based on the actions it takes without involving the controller in the fast failure recovery procedure.

/pdf/software-based-fast-failure-recovery-in-load-balanced-sdn-2fwx8hjc58.pdf

Software-based fast failure recovery in load balanced SDN-based datacenter networks

Use of online social networks (OSNs) undoubtedly brings the world closer. OSNs like Twitter provide a space for expressing one's opinions in a public platform. This great potential is misused by the creation of bot accounts, which spread fake news and manipulate opinions. Hence, distinguishing genuine human accounts from bot accounts has become a pressing issue for researchers. In this paper, we propose a framework based on deep learning to classify Twitter accounts as either 'human' or 'bot.' We use the information from user profile metadata of the Twitter account like description, follower count and tweet count. We name the framework 'DeeProBot,' which stands for Deep Profile-based Bot detection framework. The raw text from the description field of the Twitter account is also considered a feature for training the model by embedding the raw text using pre-trained Global Vectors (GLoVe) for word representation. Using only the user profile-based features considerably reduces the feature engineering overhead compared with that of user timeline-based features like user tweets and retweets. DeeProBot handles mixed types of features including numerical, binary, and text data, making the model hybrid. The network is designed with long short-term memory (LSTM) units and dense layers to accept and process the mixed input types. The proposed model is evaluated on a collection of publicly available labeled datasets. We have designed the model to make it generalizable across different datasets. The model is evaluated using two ways: testing on a hold-out set of the same dataset; and training with one dataset and testing with a different dataset. With these experiments, the proposed model achieved AUC as high as 0.97 with a selected set of features. 

/pdf/deeprobot-a-hybrid-deep-neural-network-model-for-social-bot-3tsi7dqp.pdf

DeeProBot: a hybrid deep neural network model for social bot detection based on user profile data

Internet users have been faced with a lot of threats with the growth of malware around the world. Ransomware, one of the significant types of malware, encrypts sensitive information and will not release the files until the user paid a ransom. Internet of Things (IoT) structure is an extensive area of Internet-associated instruments with additional computational capabilities with storage capacities that have the potential to be harmed by ransomware developers. The IoT has been speedily becoming more intense over the earlier years, and meanwhile, in these phases, one of the weakest areas is security. Security affairs had continued to be a crucial worry for businesses, despite the efficiency and prevalence of IoT growth. Therefore, the paper presents a machine learning model to detect ransomware attacks on IoT devices. The study used Power—to track and review the power consumption in 500 ms internals of all operating processes. The paper used three devices to perform the experiments, namely: Android device, Laptop computer, and Projector. The model was used to the monitoring power consumption of IoT devices using various procedures to categorize Ransomware outside non-malicious operations. Comparing the proposed system with the existing model outperforms concerning correctness ratio, precision ratio, recall ratio, and F-measure were considered.

Application of Machine Learning for Ransomware Detection in IoT Devices

With the spread of information technology in human life, data protection is a critical task. On the other hand, malicious programs are developed, which can manipulate sensitive and critical data and restrict access to this data. Ransomware is an example of such a malicious program that encrypts data, restricts users’ access to the system or their data, and then request a ransom payment. Many types of research have been proposed for ransomware detection. Most of these methods attempt to identify ransomware by relying on program behavior during execution. The main weakness of these methods is that it is not clear how long the program should be monitored to show its real behavior. Therefore, sometimes, these researches cannot early detect ransomware. In this paper, a new method for ransomware detection is proposed that does not require running the program and uses the PE header of the executable files. To extract effective features from the PE header files, an image based on PE header is constructed. Then, according to the advantages of Convolutional Neural Networks in extracting features from images and classifying them, CNN is used. The proposed method achieves 93.33% accuracy. Our results indicate the usefulness and practicality method for ransomware detection.

A New Method for Ransomware Detection Based on PE Header Using Convolutional Neural Networks

Service Level Management in Cloud Computing

Social media has been an unavoidable part of our life over the years. As it is getting popular, the number of social media bots are also increasing. Social media bots are the artificial agents who imitate as a human on social media. They are intended to like, retweet the posts which eventually can tamper with the genuineness of the trend. They can also be a menace to democracy as they can falsely influence people. Social media bots can be used for cyberbullying, terrorist activities, gaining fame, spreading wrong information, restricting freedom of speech, spamming. To detect social media bots on Twitter, we utilized metadata of Twitter profiles and applied a unique feature selection method, and also explored the power of ensemble learning to make a robust classifier.

Enhanced Twitter bot detection using ensemble machine learning

Systematic analysis and review of path optimization techniques in WSN with mobile sink

Fault diagnosis is a central aspect of network fault management. Since faults are unavoidable in communication systems, their quick detection and isolation is essential for the robustness, reliability, and accessibility of a system. Probing technique for fault localization involves placement of probe stations (Probe stations are specially instrumented nodes from where probes can be sent to monitor the network) which affects the diagnosis capability of the probes sent by the probe stations. Probe station locations affect probing efficiency, monitoring capability, and deployment cost. At the same time, probe station selection affects the selection of probe set for fault localization. We are presenting a novel approach for minimal probe station selection with an objective to reduce probe set size that will be used for fault localization. The probe station selected through this approach results into reduced deployment cost as well as it helps in producing smaller probe set for fault localization reducing overall operation cost. We provide experimental evaluation of the proposed algorithms through simulation results.

Probe station placement algorithm for probe set reduction in network fault localization

The ransomware is an extortion-based malware. As it is an extortion-based attack, it locks/encrypts the data on victim’s machine and asks for a ransom (money). Hence, its name is ransomware. From last four to five years, some high-profile ransomware attack were reported and got attention. Recently due to WannaCry attack, which affected the British Health care system, this type of attack got attention. Many solutions have been proposed and implemented for the detection and analysis depending upon type and size of the attack. Though there are different solutions implemented and explications given for the detection and analysis, we found that there are still some shortcomings and limitations for the solutions provided. This survey paper provides the overview of the solutions that are proposed or implemented as of now for the detection and analysis of ransomware attack. It also focuses on the shortcoming or limitations for the given solutions.

Detection of Ransomware Attack: A Review

Fault diagnosis is a central aspect of network fault management. Since faults are unavoidable in communication systems, their quick detection and isolation is essential for the robustness, reliability, and accessibility of a system. Fault localization is done using probing, monitoring, with agents, agent less, through WMI etc. Probing technique for fault localization involves placement of probe stations (Probe stations are specially instrumented nodes from where probes can be sent to monitor the network) which affects the diagnosis capability of the probes sent by the probe stations. Probe station locations affect probing efficiency, monitoring capability, and deployment cost. At the same time, probe station selection affects the selection of probe set for fault localization. We are presenting a novel approach for minimal probe station selection with an objective to reduce probe set size that will be used for fault localization. The probe station selected through this approach results into reduced deployment cost as well as it helps in producing smaller probe set for fault localization reducing overall operation cost. We provide experimental evaluation of the proposed algorithm and provided analysis of same with Shadow Node Reduction (SNR) algorithm through simulation results.

Balaji Patil

Papers

Enhanced Twitter bot detection using ensemble machine learning

Systematic analysis and review of path optimization techniques in WSN with mobile sink

Probe station placement algorithm for probe set reduction in network fault localization

Detection of Ransomware Attack: A Review

Probe station placement algorithm for probe set reduction in network fault detection and localization