AppIntent

ABSTRACTAs the capabilities of mobile devices continuously improve, a lot of environments that utilize such devices extend their functionalities; as a notable example, assistive environments offer a lot of characteristics that seemed inevitable a few years ago. In the healthcare domain modern systems are able to support advanced characteristics such as those associated with remote treatment facilities. In these environments sensitive medical data are being transmitted; therefore there is a need to ensure the security properties of medical information. A number of strict security requirements often imposed by different international legislation processes emerge due to the sensitivity of data being transmitted. In addition, in the absence of fixed infrastructures and stable topologies there is a need to create secure paths end‐to‐end for secure and efficient communication. In this paper we present an architecture that allows dissemination of medical information in a secure manner in the absence of stable topologies and infrastructures built upon resource efficient devices. The presented architecture utilizes advanced management techniques, achieving secure and privacy‐preserving transmission of sensitive data. We present a combination of different techniques and with a number of initial measurements we show the effective operation of our architecture in the presence of an adequately large number of users participating in the performance test‐bed scenario. Copyright © 2010 John Wiley & Sons, Ltd.

Advances in digital communication play an important role in our daily lives in today’s world. In general, information security systems fall into two categories: encryption and information hiding. The storage and transmission of sensitive personal data have become a part of everyday life for professional and personal well-being. Therefore, the issue of secure storage and transmission of confidential information is interest to many researchers. Steganography is a collective method to hide sensitive data in unobtrusive digital media such as video, audio, and images. One of the biggest challenges in developing steganography systems is finding the right balance between metrices like reliability, security, and data privacy. This project provides information about how the Bit Plane Complexity Steganography (BPCS) technology is applied to both grayscale and color imaging techniques and assesses performance parameters such as data concealment, security and stability based on the peak signal-to-noise ratio (PSNR) and Mean Square Error (MSE) with various test cases to explain how it works for different files and images.

With the rapid development of the Internet of Things technology and the gradual upgrade of communication methods, a new type of telemedicine system encounters a golden opportunity for development. However, lots of portable sensors for medical health have generated a large amount of sensitive data while bringing convenience to people, which makes the original transmission scheme difficult to meet current transmission requirements. Aiming at realizing high efficiency of image transmission and high security of sensitive image data in the telemedicine system, this article proposes a secure and traceable image transmission scheme. The sensitive image is first compressed and encrypted by the optimized semitensor product compressed sensing algorithm. By the perceptual hash algorithm, the image hash value, also called image fingerprint, is generated from the image content to verify the authenticity of the image. All the image fingerprints are merged to form an image fingerprint chain, which provides the traceability of the image authentication. The digital watermarking technology is used to hide the encrypted sensitive image into a meaningful carrier image, which increases the transmission content without enlarging the transmission load. The experimental results show that the proposed image transmission scheme can effectively improve the transmission efficiency, the reconstruction effect, the security, and the authenticity of the image transmission in the telemedicine systems.

Confidentiality-minded framework for blockchain-based BIM design collaboration

Android applications (apps for short) frequently send users' personally identifiable data over IP networks. Previous attempts to address privacy leakage on mobiles by checking whether these sensitive data is off the device. Actually, some benign apps need to collect users' privacy information for many sensitive tasks (e.g., contacts manager, location service, or finance). Since these kinds of data transmissions provide an application's functionality, treating these as privacy leakages are false positives. In this paper, we present Android Privacy Assistant (APA), a practical privacy protection system that reveals privacy disclosure and provides fine-grained privacy information modifications to balance privacy and data usability. APA leverages machine learning to detect privacy leaks by inspecting network traffic, and uses generalization techniques to decrease privacy sensitivity. The evaluation result shows that APA can detect privacy leakage with up to 95% accuracy in our dataset and have almost no overhead on network and battery consumption.

Transmission of sensitive data over some channel is a highly security constrained scenario and thus demands the application of some encryption algorithm. It is better to implement the algorithm in hardware as compared to software due to better computational speed and memory usage. Tiny Encryption Algorithm known as TEA block cipher is a light-weight and efficient cryptographic algorithm, well suited for wireless communication systems. This paper presents the successful implementation of TEA on FPGA for different design approaches to analyze the performance and resource utilization against each design approach.

Internet of Medical Things (IoMT) and Machine Learning (ML) have become increasingly popular in healthcare. Wearable tiny medical devices can collect and transmit personal health-related data. However, applying ML-driven IoT in healthcare presents several challenges, especially in remote patient monitoring: (i) latency and privacy issues can hinder the transmission of sensitive medical data; (ii) it could require the correlation of multiple and heterogeneous data collected by different medical devices; and (iii) the limited resources of ultra-low-power wearable devices prevent the implementation of complex ML models directly on-board. On the other hand, Federated Learning (FL) and TinyML can address these limitations by enabling collaborative model training across distributed IoMT-edge resource-constrained microcontroller unit (MCU) based devices, allowing local data processing and improving latency and energy efficiency. However, traditional FL mainly handles unimodal data, limiting its direct applicability to several real-world IoT healthcare scenarios. This work proposes a Cross-Modal Federated TinyML (TinyCFL) implementation for MCU-based medical devices, which employs an intermediate multimodal distributed data fusion approach. Data from different modalities are independently processed on different tiny devices to extract features, which are then fused for healthcare tasks that require cross-modal reasoning. The proposed approach is evaluated by using the "UP-Fall detection" dataset, which is used in balanced, unbalanced, and Participant-Wise distribution scenarios. The proposed approach has been designed to be deployed in a distributed IoT-edge scenario. A prototype of the proposed TinyCFL approach based on resource-constrained MCUs has also been implemented.

IoT healthcare devices are being used to share the real time personal data of patients to their doctors. Conventionally, centralized systems are used to store personal data and for encryption decryption, property server performed the duty. But those systems give rise to security and response time issues e.g. data breaching while moving the data between devices and server as there are IoT devices which send their data (blood pressure, heart beat rate etc.) as plain text to server and server have to perform encryption/decryption according to the need. Apart this, server have to response back the requests of different healthcare provider’s devices which may increase the response time. Therefore, security and response time are the main issues to be handled. There is a need of system that makes the secure transmission of sensitive healthcare data. We recommend some suggestions to improve those areas.

Medical applications have already been integrated into mobile devices (e.g. Tablet PCs, PDAs and smart phones) and are being used by medical personnel in treatment centers, for retrieving and examining patient's Electronic Health Records (EHR). In such mobile healthcare applications, specific attention is drawn towards the security requirements since the transmission of sensitive medical data through a public network renders the problem of communication privacy. In this paper we present an approach to transfer the medical records of an individual by using the existing infrastructure of mobile operators. To achieve that, we propose the application of existing technologies in 3G networks such as the generic bootstrapping architecture (GBA) to enable the secure transfer of EHR data. The paper presents the corresponding applicability scenarios, initial results from a prototype test bed and discusses the feasibility of the proposed solution along with its limitations

Do My Emotions Influence What I Share? Analysing the Effects of Emotions on Privacy Leakage in Twitter

With the wide application of machine learning technology, more and more sensitive data were used to develop the machine learning model. Unfortunately, machine learning systems have been shown to be vulnerable to various privacy leakage attacks, such as membership inference attacks and model inversion attacks. These privacy threats break down the confidentiality of the training data; what’s more, the leakage of sensitive privacy will reduce the enthusiasm of data owners for sharing data with the machine learning system. Without enough training data, more seriously, it will hinder the application of machine learning. Therefore, it requires analyzing strategies for privacy risks to help data owners pre-assess the candidate dataset and assist data owners in implementing reasonable privacy control. However, the systematic privacy risk assessment is still absent from the data owner’s perspective.This paper investigates and analyzes machine learning privacy risks to understand the relationship between training data properties and privacy leakage. Based on this recognition, we introduce a privacy risk assessment scheme based on the clustering distance of training data. Our clustering distance-based method can reflect the privacy risk level of a different individual data record. And then, we combine both existing privacy analysis based on data features and our clustering distance-based method to investigate privacy risks systematically. Our experiments showed that our clustering distance method and other set properties are tightly related to privacy leakage. And data owners can pre-assess the privacy risks of candidate datasets before uploading or sharing them to the machine learning model. If needed, decide to re-choose the dataset to reduce privacy risks to an acceptable level.

Received signal strength (RSS) fingerprint-based indoor localization has received increasing popularity over the past decades. However, it suffers from the high calibration effort for fingerprint collection. In this paper, a Centralized indooR localizatioN method using Pseudo-label (CRNP) is proposed, which employs a small set of labeled data (RSS fingerprint) along with large volumes of unlabeled data (RSS values without coordinates) to reduce the workload of labeled data collection and improve the indoor localization performance. However, the rich location data is large in quantity and privacy sensitive, which may lead to high network cost (i.e., data transmission cost, data storage cost) and potential privacy leakage for data transmission to the central server. Therefore, a decentralized indoor localization method incorporating CRNP and federated learning is devised, which keeps the location data on local users' devices and improves the shared CRNP model by aggregating users' updates of the model. The experiment results demonstrate that (i) the proposed CRNP enables to improve the indoor localization accuracy by using unlabeled crowdsourced data; (ii) the designed decentralized scheme is robust to different data distribution and is capable to reduce the network cost and prevent users' privacy leakage.

Nowadays, touchscreen mobile phones make up a larger and larger share in the mobile market. Users also often use their mobile phones (e.g., Android phones) to store personal and sensitive data. It is therefore important to safeguard mobile phones by authenticating legitimate users and detecting impostors. In this paper, we propose a novel user authentication scheme based on touch dynamics that uses a set of behavioral features related to touch dynamics for accurate user authentication. In particular, we construct and select 21 features that can be used for user authentication. To evaluate the performance of our scheme, we collect and analyze touch gesture data of 20 Android phone users by comparing several known machine learning classifiers. The experimental results show that a neural network classifier is well-suited to authenticate different users with an average error rate of about 7.8% for our selected features. Finally, we optimize the neural network classifier by using Particle Swarm Optimization (PSO) to deal with variations in users’ usage patterns. Experimental results show that the average error rate of our optimized scheme is only about 3%, achieved solely by analyzing the touch behavior of users on an Android phone.

Distributed learning over data from sensor-based networks has been adopted to collaboratively train models on these sensitive data without privacy leakages. We present a distributed learning framework that involves the integration of secure multi-party computation and differential privacy. In our differential privacy method, we explore the potential of output perturbation and gradient perturbation and also progress with the cutting-edge methods of both techniques in the distributed learning domain. In our proposed multi-scheme output perturbation algorithm (MS-OP), data owners combine their local classifiers within a secure multi-party computation and later inject an appreciable amount of statistical noise into the model before they are revealed. In our Adaptive Iterative gradient perturbation (MS-GP) method, data providers collaboratively train a global model. During each iteration, the data owners aggregate their locally trained models within the secure multi-party domain. Since the conversion of differentially private algorithms are often naive, we improve on the method by a meticulous calibration of the privacy budget for each iteration. As the parameters of the model approach the optimal values, gradients are decreased and therefore require accurate measurement. We, therefore, add a fundamental line-search capability to enable our MS-GP algorithm to decide exactly when a more accurate measurement of the gradient is indispensable. Validation of our models on three (3) real-world datasets shows that our algorithm possesses a sustainable competitive advantage over the existing cutting-edge privacy-preserving requirements in the distributed setting.

With the development of cloud computing, the sensitive information of outsourced data is at risk of unauthorized accesses. To protect data privacy, the sensitive data should be encrypted by the data owner before outsourcing, which makes the traditional and efficient plaintext keyword search technique useless. Hence, it is an especially important thing to explore secure encrypted cloud data search service. Considering the huge number of outsourced data, there are three problems we are focused on to enable efficient search service: multi-keyword search, result relevance ranking and dynamic update. In this paper, we propose a practically efficient and flexible searchable encrypted scheme which supports both multi-keyword ranked search and dynamic update. To support multi-keyword search and result relevance ranking, we adopt Vector Space Model (VSM) to build the searchable index to achieve accurate search result. To improve search efficiency, we design a tree-based index structure which supports insertion and deletion update well without privacy leakage. We propose a secure search scheme to meet the privacy requirements in the threat model. Finally, experiments on real-world dataset are implemented to demonstrate the overall performance of the proposed scheme, which show our scheme is efficient.