Description:
Industrial Internet of Things (IIoT) deploys edge devices to act as intermediaries between sensors and actuators and application servers or cloud services. Machine learning models have been widely used to thwart malware attacks in such edge devices. However, these models are vulnerable to adversarial attacks where attackers craft adversarial samples by introducing small perturbations to malware samples to fool a classifier to misclassify them as benign applications. Literature on deep learning networks proposes adversarial retraining as a defense mechanism where adversarial samples are combined with legitimate samples to retrain the classifier. However, existing works select such adversarial samples in a random fashion which degrades the classifier's performance. This work proposes two novel approaches for selecting adversarial samples to retrain a classifier. One, based on the distance from malware cluster center, and the other, based on a probability measure derived from a kernel based learning (KBL). Our experiments show that both of our sample selection methods outperform the random selection method and the KBL selection method improves detection accuracy by 6%. Also, while existing works focus on deep neural networks with respect to adversarial retraining, we additionally assess the impact of such adversarial samples on other classifiers and our proposed selective adversarial retraining approaches show similar performance improvement for these classifiers as well. The outcomes from the study can assist in designing robust security systems for IIoT applications.
Description:
Industrial Internet of Things (IIoT) deploys edge devices to act as intermediaries between sensors and actuators and application servers or cloud services. Machine learning models have been widely used to thwart malware attacks in such edge devices. However, these models are vulnerable to adversarial attacks where attackers craft adversarial samples by introducing small perturbations to malware samples to fool a classifier to misclassify them as benign applications. Literature on deep learning networks proposes adversarial retraining as a defense mechanism where adversarial samples are combined with legitimate samples to retrain the classifier. However, existing works select such adversarial samples in a random fashion which degrades the classifier's performance. This work proposes two novel approaches for selecting adversarial samples to retrain a classifier. One, based on the distance from malware cluster center, and the other, based on a probability measure derived from a kernel based learning (KBL). Our experiments show that both of our sample selection methods outperform the random selection method and the KBL selection method improves detection accuracy by 6%. Also, while existing works focus on deep neural networks with respect to adversarial retraining, we additionally assess the impact of such adversarial samples on other classifiers and our proposed selective adversarial retraining approaches show similar performance improvement for these classifiers as well. The outcomes from the study can assist in designing robust security systems for IIoT applications.
Description:
In this paper, we propose a new type of adaptive fuzzy inference system with a view to achieve improved performance for forecasting nonlinear time series data by dynamically adapting the fuzzy rules with arrival of new data. The structure of the fuzzy model utilized in the proposed system is developed based on the log-likelihood value of each data vector generated by a trained Hidden Markov Model. As part of its adaptation process, our system checks and computes the parameter values and generates new fuzzy rules as required, in response to new observations for obtaining better performance. In addition, it can also identify the most appropriate fuzzy rule in the system that covers the new data; and thus requires to adapt the parameters of the corresponding rule only, while keeping the rest of the model unchanged. This intelligent adaptive behavior enables our adaptive fuzzy inference system (FIS) to outperform standard FISs. We evaluate the performance of the proposed approach for forecasting stock price indices. The experimental results demonstrate that our approach can predict a number of stock indices, e.g., Dow Jones Industrial (DJI) index, NASDAQ index, Standard and Poor500 (S&P500) index and few other indices from UK (FTSE100), Germany (DAX) , Australia (AORD) and Japan (NIKKEI) stock markets, accurately compared with other existing computational and statistical methods.
Description:
Wireless sensor networks (WSNs) will be an integral part of the future Internet of Things (loT) environment and generate large volumes of data. However, these data would only be of benefit if useful knowledge can be mined from them. A data mining framework for WSNs includes data extraction, storage and mining techniques, and must be efficient and dependable. In this paper, we propose a new type of behavioral pattern mining technique from sensor data called regularly frequent sensor patterns (RFSPs). RFSPs can identify a set of temporally correlated sensors which can reveal significant knowledge from the monitored data. A distributed data extraction model to prepare the data required for mining RFSPs is proposed, as the distributed scheme ensures higher availability through greater redundancy. The tree structure for RFSP is compact requires less memory and can be constructed using only a single scan through the dataset, and the mining technique is efficient with low runtime. Current mining techniques in the literature on sensor data employ a single memory-based sequential approach and hence are not efficient. Moreover, usage of the. MapReduce model for the distributed solution has not been explored extensively. Since MapReduce is becoming the de facto model for computation on large data, we also propose a parallel implementation of the RFSP mining algorithm, called RFSP on Hadoop (RFSP-H), which uses a MapReduce-based framework to gain further efficiency. Experiments conducted to evaluate the compactness and performance of the data extraction model, RFSP-tree and RFSP-H mining show improved results. (C) 2016 Elsevier Inc. All rights reserved.
Description:
Simulation is a cost effective, fast and flexible alternative to test-beds or practical deployment for evaluating the characteristics and potential of mobile ad hoc networks. Since environmental context and mobility have a great impact on the accuracy and efficacy of performance measurement, it is of paramount importance how closely the mobility of a node resembles its movement pattern in a real-world scenario. The existing mobility models mostly assume either free space for deployment and random node movement or the movement pattern does not emulate real-world situation properly in the presence of obstacles because of their generation of restricted paths. This demands for the development of a node movement pattern with accurately representing any obstacle and existing path in a complex and realistic deployment scenario. In this paper, we propose a general mobility model capable of creating a more realistic node movement pattern by exploiting the concept of flexible positioning of anchors. Since the model places anchors depending upon the context of the environment through which nodes are guided to move towards the destination, it is capable of representing any terrain realistically. Furthermore, obstacles of arbitrary shapes with or without doorways and any existing pathways in full or part of the terrain can be incorporated which makes the simulation environment more realistic. A detailed computational complexity has been analyzed and the characteristics of the proposed mobility model in the presence of obstacles in a university campus map with and without signal attenuation are presented which illustrates its significant impact on performance evaluation of wireless ad hoc networks.
Description:
Predicting the secondary structure of proteins from a primary sequence alone has been variously approached from either a classification or a generative model perspective. The most prominent classification methods have used neural networks, which involves mappings from a local window of residues in the sequence to the structural state of the central residue in the window, thus capturing the local interactions effectively. However, they fail to capture distant interactions among residues. The generative models based on Bayesian segmentation capture sequence structure relationships using generalized hidden Markov models with explicit state duration. They capture non-local interactions through a joint sequence-structure probability distribution based on structural segments. In this paper, we investigate a combined architecture of Bayesian segmentation at the first stage and neural network at the second stage which captures both local and non-local correlation, to increase the single sequence prediction accuracy. The combined architecture is further enhanced by using neural network optimization and ensemble techniques.
Description:
In this paper, we introduce a new hybrid of Hidden Markov Model (HMM), Fuzzy Logic and multiobjective Evolutionary Algorithm (EA) for building a fuzzy model to predict non-linear time series data. In this hybrid approach, the HMM's log-likelihood score for each data pattern is used to rank the data and fuzzy rules are generated using the ranked data. We use multiobjective EA to find a range of trade-off solutions between the number of fuzzy rules and the prediction accuracy. The model is tested on a number of benchmark and more recent financial time series data. The experimental results clearly demonstrate that our model is able to generate a reduced number of fuzzy rules with similar (and in some cases better) performance compared with typical data driven fuzzy models reported in the literature.
Description:
To ensure customer satisfaction and greater market acceptance, voice over Wi-Fi networks must ensure voice quality under various network parameters, configurations and traffic conditions, and other practical effects, e.g., channel noise, and capturing effects. An accurate voice capacity estimation model considering these factors can greatly assist network designers. In the current work, we propose an analytical model to estimate voice over Internet Protocol (VoIP) capacity over Wi-Fi networks addressing these issues. We employ widely used ITU-T E-model to assess voice quality and VoIP call capacity is presented in the form of an optimization problem with voice quality requirement as a constraint. In particular, we analyze delay and loss in channel access and queue, and their impacts on voice quality. The proposed capacity model is first developed for a single hop wireless local area network (WLAN) and then extended for multihop scenarios. To model real network scenario closely, we also consider channel noise and capture effect, and analyze the impacts of transmission range, interference range, and WLAN radius. In absence of any existing call capacity model that considers all the above factors concomitantly, our proposed model will be extremely useful to network designers and voice capacity planners.