Arun Balaji Buduru

A Reference Architecture for Improving Security and Privacy in Internet of Things Applications

As the promise of the Internet of Things (IoT) materializes in our everyday lives, we are often challenged with a number of concerns regarding the efficacy of the current data privacy solutions that support the pervasive components at play in IoT. The privacy and security concerns surrounding IoT often manifests themselves as a treat to end-user adoption and negatively impacts trust among end-users in these solutions. In this paper, we present a reference software architecture for building cloud-enabled IoT applications in support of collaborative pervasive systems aimed at achieving trustworthiness among end-users in IoT scenarios. We present a case study that leverages this reference architecture to protect sensitive user data in an IoT application implementation and evaluate the response of an end-user study accomplished through a survey.

An Effective Approach to Continuous User Authentication for Touch Screen Smart Devices

Due to the rapid increase in the use of personal smart devices, more sensitive data is stored and viewed on these smart devices. This trend makes it easier for attackers to access confidential data by physically compromising (including stealing) these smart devices. Currently, most personal smart devices employ one of the one-time user authentication schemes, such as four-to-six digits, fingerprint or pattern-based schemes. These authentication schemes are often not good enough for securing personal smart devices because the attackers can easily extract all the confidential data from the smart device by breaking such schemes, or by keeping the authenticated session open on a physically compromised smart device. In addition, existing re-authentication or continuous authentication techniques for protecting personal smart devices use centralized architecture and require servers at a centralized location to train and update the learning model used for continuous authentication, which impose additional communication overhead. In this paper, an approach is presented to generating and updating the authentication model on the users smart device with users gestures, instead of a centralized server. There are two major advantages in this approach. One is that this approach continuously learns and authenticates finger gestures of the user in the background without requiring the user to provide specific gesture inputs. The other major advantage is to have better authentication accuracy by treating uninterrupted user finger gestures over a short time interval as a single gesture for continuous user authentication.

Attack Detection in Cloud Infrastructures Using Artificial Neural Network with Genetic Feature Selection

Detecting cyber-attacks in cloud infrastructures is essential for protecting cloud infrastructures from cyber-attacks. It is difficult to detect cyber-attacks in cloud infrastructures due to the complex and distributed natures of cloud infrastructures. In addition, various computing and storage devices, both mobile and stationary, are connected to cloud infrastructures to facilitate users access, which increases the difficulty and complexity of cyber-attack detection. In this paper, an effective approach is presented to detecting cyber-attacks in cloud infrastructures, including those through remote computing devices. This approach is to use an artificial neural network (ANN), which is trained using the network traffic data on the connecting links of the cloud infrastructures. Since ANN is computationally intensive, a technique using a genetic algorithm to reduce the number of features extracted from the network traffic data is developed and incorporated in our approach. This approach is illustrated by using two large data sets of network traffic, and shown that the results are better than those of existing methods for detecting cyber-attacks in cloud infrastructures.

An adaptable distributed trust management framework for large-scale secure service-based systems

A major advantage of service-based computing systems is the ability to enable rapid formation of large-scale distributed systems by composing available services to achieve the system goals, regardless of the programming languages and platforms used to develop and/or run these services. For these systems, which often involve communications among multiple organizations over various networks, high confidence and adaptability are of primary concern to ensure that users can access these systems anywhere and anytime through various devices, knowing that their security and privacy are well protected under various situations. In this paper, an adaptable distributed trust management framework for large-scale service-based systems is presented. This framework includes a meta-model with a formal specification language for situation-aware security policies, and tools for generating and deploying security agents to evaluate and enforce trust decisions based on security policies, credentials and situational information. With this framework, large-scale service-based systems can incorporate distributed trust management to meet their trustworthiness requirements under various situations.

Protecting Critical Cloud Infrastructures with Predictive Capability

Emerging trends in cyber system security breaches, including those in critical infrastructures involving cloud systems, such as in applications of military, homeland security, finance, utilities and transportation systems, have shown that attackers have abundant resources, including both human and computing power, to launch attacks. The sophistication and resources used in attacks reflect that the attackers may be supported by large organizations and in some cases by foreign governments. Hence, there is an urgent need to develop intelligent cyber defense approaches to better protecting critical cloud infrastructures. In order to have much better protection for critical cloud infrastructures, effective approaches with predictive capability are needed. Much research has been done by applying game theory to generating adversarial models for predictive defense of critical infrastructures. However, these approaches have serious limitations, some of which are due to the assumptions used in these approaches, such as rationality and Nash equilibrium, which may not be valid for current and emerging cloud infrastructures. Another major limitation of these approaches is that they do not capture probabilistic human behaviors accurately, and hence do not incorporate human behaviors. In order to greatly improve the protection of critical cloud infrastructures, it is necessary to predict potential security breaches on critical cloud infrastructures with accurate system-wide causal relationship and probabilistic human behaviors. In this paper, the challenges and our vision on developing such proactive protection approaches are discussed.