A novel fault-tolerant privacy-preserving cloud-based data aggregation scheme for lightweight health data.

Mobile health networks (MHNWs) have facilitated instant medical health care and remote health monitoring for patients. Currently, a vast amount of health data needs to be quickly collected, processed and analyzed. The main barrier to doing so is the limited amount of the computational storage resources that are required for MHNWs. Therefore, health data must be outsourced to the cloud. Although the cloud has the benefits of powerful computation capabilities and intensive storage resources, security and privacy concerns exist. Therefore, our study examines how to collect and aggregate these health data securely and efficiently, with a focus on the theoretical importance and application potential of the aggregated data. In this work, we propose a novel design for a private and fault-tolerant cloud-based data aggregation scheme. Our design is based on a future ciphertext mechanism for improving the fault tolerance capabilities of MHNWs. Our scheme is privatized via differential privacy, which is achieved by encrypting noisy health data and enabling the cloud to obtain the results of only the noisy sum. Our scheme is efficient, reliable and secure and combines different approaches and algorithms to improve the security and efficiency of the system. Our proposed scheme is evaluated with an extensive simulation study, and the simulation results show that it is efficient and reliable. The computational cost of our scheme is significantly less than that of the related scheme. The aggregation error is minimized from ${\rm{O}}\left( {\sqrt {{\bf{w + 1}}} } \right)$ in the related scheme to O(1) in our scheme.

Anomaly detection over differential preserved privacy in online social networks.

The massive reach of social networks (SNs) has hidden their potential concerns, primarily those related to information privacy. Users increasingly rely on social networks for more than merely interactions and self-representation. However, social networking environments are not free of risks. Users are often threatened by privacy breaches, unauthorized access to personal information, and leakage of sensitive data. In this paper, we propose a privacy-preserving model that sanitizes the collection of user information from a social network utilizing restricted local differential privacy (LDP) to save synthetic copies of collected data. This model further uses reconstructed data to classify user activity and detect abnormal network behavior. Our experimental results demonstrate that the proposed method achieves high data utility on the basis of improved privacy preservation. Moreover, LDP sanitized data are suitable for use in subsequent analyses, such as anomaly detection. Anomaly detection on the proposed method's reconstructed data achieves a detection accuracy similar to that on the original data.

PPSDT: A Novel Privacy-Preserving Single Decision Tree Algorithm for Clinical Decision-Support Systems Using IoT Devices.

Medical service providers offer their patients high quality services in return for their trust and satisfaction. The Internet of Things (IoT) in healthcare provides different solutions to enhance the patient-physician experience. Clinical Decision-Support Systems are used to improve the quality of health services by increasing the diagnosis pace and accuracy. Based on data mining techniques and historical medical records, a classification model is built to classify patients' symptoms. In this paper, we propose a privacy-preserving clinical decision-support system based on our novel privacy-preserving single decision tree algorithm for diagnosing new symptoms without exposing patients' data to different network attacks. A homomorphic encryption cipher is used to protect users' data. In addition, the algorithm uses nonces to avoid one party from decrypting other parties' data since they all will be using the same key pair. Our simulation results have shown that our novel algorithm have outperformed the Naïve Bayes algorithm by 46.46%; in addition to the effects of the key value and size on the run time. Furthermore, our model is validated by proves, which meet the privacy requirements of the hospitals' datasets, frequency of attribute values, and diagnosed symptoms.

A Randomized Watermarking Technique for Detecting Malicious Data Injection Attacks in Heterogeneous Wireless Sensor Networks for Internet of Things Applications.

Using Internet of Things (IoT) applications has been a growing trend in the last few years. They have been deployed in several areas of life, including secure and sensitive sectors, such as the military and health. In these sectors, sensory data is the main factor in any decision-making process. This introduces the need to ensure the integrity of data. Secure techniques are needed to detect any data injection attempt before catastrophic effects happen. Sensors have limited computational and power resources. This limitation creates a challenge to design a security mechanism that is both secure and energy-efficient. This work presents a Randomized Watermarking Filtering Scheme (RWFS) for IoT applications that provides en-route filtering to remove any injected data at an early stage of the communication. Filtering injected data is based on a watermark that is generated from the original data and embedded directly in random places throughout the packet's payload. The scheme uses homomorphic encryption techniques to conceal the report's measurement from any adversary. The advantage of homomorphic encryption is that it allows the data to be aggregated and, thus, decreases the packet's size. The results of our proposed scheme prove that it improves the security and energy consumption of the system as it mitigates some of the limitations in the existing works.

Report: Nuclei segmentation of leukocytes in blood smear digital images.

The Leukocytes are differentiated from each other on the basis of their nuclei, demanded in many Medical studies, especially in all types of Leukemia by the Hematologists to note the disorder caused by specific type of Leukocyte. Leukemia is a life threatening disease. The work for diagnosing is manually carried out by the Hematologists involving much labor, time and human errors. The problems mentioned are easily addressed through computer vision techniques, but still accuracy and efficiency are demanded in terms of the basic and challenging step segmentation of Leukocyte's nuclei. The underlying study proposed better method in terms of accuracy and efficiency by designing a dynamic convolution filter for boosting low intensity values in the separated green channel of an RGB image and suppressing the high values in the same channel. The high values in the green channel become 255 (background) while the nuclei always have low values in the green channel and thus clearly appear as foreground. The proposed technique is tested on 365 images achieving an overall accuracy of 95.89%, while improving the efficiency by 10%. The proposed technique achieved its targets in a realistic way by improving the accuracy as well as the efficiency and both are highly required in the area.

Intelligent bar chart plagiarism detection in documents.

This paper presents a novel features mining approach from documents that could not be mined via optical character recognition (OCR). By identifying the intimate relationship between the text and graphical components, the proposed technique pulls out the Start, End, and Exact values for each bar. Furthermore, the word 2-gram and Euclidean distance methods are used to accurately detect and determine plagiarism in bar charts.