Search for: All records

Individuals spend a significant portion of their time on social media. It has become a platform for expression of feelings, sharing of ideas and connecting with other individuals using video and audio posts, textual data such as comments and descriptions and so on. Social media has a considerable impact on people’s daily life. In recent time, there is an enormous growth in number of people using Twitter and Instagram to share their emotions and sentiments which represents their actual feelings. In this work, we apply Machine Learning techniques on social media data to perform a comprehensive investigation to detect the risk of depression in people. Our work can help to detect various symptoms such sadness, loneliness, detachment etc. providing an insight for forensic analysts and law enforcement agencies about the person’s mental state. The experimental results show that Extra Tree Classifier performs significantly better over the other models in detecting the sentiment of people using social media data. 

The adoption of blockchain in the Internet of Things (IoT) has been increasing due to the various benefits that blockchain brings, such as security and privacy. Current blockchain models for mobile IoT assume there are fixed, powerful edge devices capable of providing global communication to all the nodes in the network. However, due to the mobile nature of IoT or network partitioning problems (NPP), nodes can move out of a cell area and split into smaller independent peer-to-peer subnetworks. Existing blockchain structures either do not support the network partitioning problem or have limitations. This paper introduces a multidimensional, graph-based blockchain structure, that utilizes k-dimensional spatiotemporal space, to address the challenges of applying blockchain in mobile networks with limited resources. Experimental results show that a multidimensional blockchain structure can improve scalability and efficiency as the blockchain grows in size, similar to logarithmic growth, and reduce the longest chain length by more than 99.99% compared to the traditional chain-based blockchain structure. 

The adoption of blockchain in the Internet of Things (IoT) has been increasing due to the various benefits that blockchain brings, such as security and privacy. Current blockchain models for mobile IoT assume there are fixed, powerful edge devices capable of providing global communication to all the nodes in the network. However, due to the mobile nature of IoT or network partitioning problems (NPP), nodes can move out of a cell area and split into smaller independent peer-to-peer subnetworks. Existing blockchain structures either do not support the network partitioning problem or have limitations. This paper introduces a multidimensional, graph-based blockchain structure, that utilizes k-dimensional spatiotemporal space, to address the challenges of applying blockchain in mobile networks with limited resources. Experimental results show that a multidimensional blockchain structure can improve scalability and efficiency as the blockchain grows in size, similar to logarithmic growth, and reduce the longest chain length by more than 99.99% compared to the traditional chain-based blockchain structure. 

Research is increasingly showing the tremendous vulnerability in machine learning models to seemingly undetectable adversarial inputs. One of the current limitations in adversarial machine learning research is the incredibly time-consuming testing of novel defenses against various attacks and across multiple datasets, even with high computing power. To address this limitation, we have developed Jespipe as a new plugin-based, parallel-by-design Open MPI framework that aids in evaluating the robustness of machine learning models. The plugin-based nature of this framework enables researchers to specify any pre-training data manipulations, machine learning models, adversarial models, and analysis or visualization metrics with their input Python files. Because this framework is plugin-based, a researcher can easily incorporate model implementations using popular deep learning libraries such as PyTorch, Keras, TensorFlow, Theano, or MXNet, or adversarial robustness tools such as IBM’s Adversarial Robustness Toolbox or Foolbox. The parallelized nature of this framework also enables researchers to evaluate various learning or attack models with multiple datasets simultaneously by specifying all the models and datasets they would like to test with our XML control file template. Overall, Jespipe shows promising results by reducing latency in adversarial machine learning algorithm development and testing compared to traditional Jupyter notebook workflows. 

The conventional machine learning (ML) and deep learning (DL) methods use large amount of data to construct desirable prediction models in a central fusion center for recognizing human activities. However, such model training encounters high communication costs and leads to privacy infringement. To address the issues of high communication overhead and privacy leakage, we employed a widely popular distributed ML technique called Federated Learning (FL) that generates a global model for predicting human activities by combining participated agents’ local knowledge. The state-of-the-art FL model fails to maintain acceptable accuracy when there is a large number of unreliable agents who can infuse false model, or, resource-constrained agents that fails to perform an assigned computational task within a given time window. We developed an FL model for predicting human activities by monitoring agent’s contributions towards model convergence and avoiding the unreliable and resource-constrained agents from training. We assign a score to each client when it joins in a network and the score is updated based on the agent’s activities during training. We consider three mobile robots as FL clients that are heterogeneous in terms of their resources such as processing capability, memory, bandwidth, battery-life and data volume. We consider heterogeneous mobile robots for understanding the effects of real-world FL setting in presence of resource-constrained agents. We consider an agent unreliable if it repeatedly gives slow response or infuses incorrect models during training. By disregarding the unreliable and weak agents, we carry-out the local training of the FL process on selected agents. If somehow, a weak agent is selected and started showing straggler issues, we leverage asynchronous FL mechanism that aggregate the local models whenever it receives a model update from the agents. Asynchronous FL eliminates the issue of waiting for a long time to receive model updates from the weak agents. To the end, we simulate how we can track the behavior of the agents through a reward-punishment scheme and present the influence of unreliable and resource-constrained agents in the FL process. We found that FL performs slightly worse than centralized models, if there is no unreliable and resource-constrained agent. However, as the number of malicious and straggler clients increases, our proposed model performs more effectively by identifying and avoiding those agents while recognizing human activities as compared to the stateof-the-art FL and ML approaches. 

In this work, we demonstrate the design and implementation of a novel privacy-preserving blockchain for the resource-constrained Internet of Things (IoT). Blockchain, by design, ensures trust, provides built-in integrity of information and security of immutability in an IoT system without the need of a centralized entity. However, its slow transaction rate, lack of transaction privacy, and high resource consumption are three of the major hindrances to the practical realization of blockchain in IoT. While directed acyclic graphs (DAG)-based blockchain variants (e.g., hashgraph) improve the transaction rate, the other two problems remain open. To this end, we designed and constructed the prototype of a blockchain by utilizing the benefits of high transaction rate and miner-free transaction validation process from hashgraph. The proposed blockchain, coined as PrivLiteChain, implements the concept of local differential privacy to provide transaction privacy and temporal constraint to the lifecycle of the blockchain to make it lightweight. 

Recently, blockchain has received much attention from the mobility-centric Internet of Things (IoT). It is deemed the key to ensuring the built-in integrity of information and security of immutability by design in the peer-to-peer network (P2P) of mobile devices. In a permissioned blockchain, the authority of the system has control over the identities of its users. Such information can allow an ill-intentioned authority to map identities with their spatiotemporal data, which undermines the location privacy of a mobile user. In this paper, we study the location privacy preservation problem in the context of permissioned blockchain-based IoT systems under three conditions. First, the authority of the blockchain holds the public and private key distribution task in the system. Second, there exists a spatiotemporal correlation between consecutive location-based transactions. Third, users communicate with each other through short-range communication technologies such that it constitutes a proof of location (PoL) on their actual locations. We show that, in a permissioned blockchain with an authority and a presence of a PoL, existing approaches cannot be applied using a plug-and-play approach to protect location privacy. In this context, we propose BlockPriv, an obfuscation technique that quantifies, both theoretically and experimentally, the relationship between privacy and utility in order to dynamically protect the privacy of sensitive locations in the permissioned blockchain. 

The Internet of Things (IoT), forming the foundation of Cyber Physical Systems (CPS), connects a huge number of ubiquitous sensing and mobile computing devices. The mobile IoT systems generate an enormous volume of a variety of dynamic context data and typically count on centralized architectures to process them. However, their inability to ensure security and decline in communication efficiency and response time with the increase in the size of IoT network are some of the many concerning weaknesses that are holding back the fast-paced growth of IoT. Realizing the limitations of centralized systems, recently blockchain-based decentralized architecture is being considered as the key to redesigning the IoT systems in a way that is designed to be secure, transparent, highly resistant to outages, auditable, and efficient. However, before realizing the new promise of blockchain for IoT, there are significant challenges to address. One fundamental challenge is the scale issue around data collection, storage, and analytic as IoT sensor devices possess limited computational power and storage capabilities. In particular, since the chain is always growing, IoT devices require more and more resources. Thus, an oversized chain poses storage and scalability problems. With this in mind, the overall goal of our research is to design a lightweight scalable blockchain framework for IoT of mobile devices. This framework, coined as "Sensor-Chain", promises a new generation of lightweight blockchain management with a superior reduction in resource consumption, and at the same time capable of retaining critical information about the IoT systems of mobile devices.