A Survey on Privacy Preservation in Fog-Enabled Internet of Things

Despite the rapid growth and advancement in the Internet of Things (IoT ), there are critical challenges that need to be addressed before the full adoption of the IoT. Data privacy is one of the hurdles towards the adoption of IoT as there might be potential misuse of users’ data and their identity in IoT applications. Several researchers have proposed different approaches to reduce privacy risks. However, most of the existing solutions still suffer from various drawbacks, such as huge bandwidth utilization and network latency, heavyweight cryptosystems, and policies that are applied on sensor devices and in the cloud. To address these issues, fog computing has been introduced for IoT network edges providing low latency, computation, and storage services. In this survey, we comprehensively review and classify privacy requirements for an in-depth understanding of privacy implications in IoT applications. Based on the classification, we highlight ongoing research efforts and limitations of the existing privacy-preservation techniques and map the existing IoT schemes with Fog-enabled IoT schemes to elaborate on the benefits and improvements that Fog-enabled IoT can bring to preserve data privacy in IoT applications. Lastly, we enumerate key research challenges and point out future research directions.

Evolutionary tree-based quasi identifier and federated gradient privacy preservations over big healthcare data

<span>Big data has remodeled the way organizations supervise, examine and leverage data in any industry. To safeguard sensitive data from public contraventions, several countries investigated this issue and carried out privacy protection mechanism. With the aid of quasi-identifiers privacy is not said to be preserved to a greater extent. This paper proposes a method called evolutionary tree-based quasi-identifier and federated gradient (ETQI-FD) for privacy preservations over big healthcare data. The first step involved in the ETQI-FD is learning quasi-identifiers. Learning quasi-identifiers by employing information loss function separately for categorical and numerical attributes accomplishes both the largest dissimilarities and partition without a comprehensive exploration between tuples of features or attributes. Next with the learnt quasi-identifiers, privacy preservation of data item is made by applying federated gradient arbitrary privacy preservation learning model. This model attains optimal balance between privacy and accuracy. In the federated gradient privacy preservation learning model, we evaluate the determinant of each attribute to the outputs. Then injecting Adaptive Lorentz noise to data attributes our ETQI-FD significantly minimizes the influence of noise on the final results and therefore contributing to privacy and accuracy. An experimental evaluation of ETQI-FD method achieves better accuracy and privacy than the existing methods.</span>

Privacy-Preserving Federated Learning Using Homomorphic Encryption

Federated learning (FL) is a machine learning technique that enables distributed devices to train a learning model collaboratively without sharing their local data. FL-based systems can achieve much stronger privacy preservation since the distributed devices deliver only local model parameters trained with local data to a centralized server. However, there exists a possibility that a centralized server or attackers infer/extract sensitive private information using the structure and parameters of local learning models. We propose employing homomorphic encryption (HE) scheme that can directly perform arithmetic operations on ciphertexts without decryption to protect the model parameters. Using the HE scheme, the proposed privacy-preserving federated learning (PPFL) algorithm enables the centralized server to aggregate encrypted local model parameters without decryption. Furthermore, the proposed algorithm allows each node to use a different HE private key in the same FL-based system using a distributed cryptosystem. The performance analysis and evaluation of the proposed PPFL algorithm are conducted in various cloud computing-based FL service scenarios.

Facial Privacy Preservation using FGSM and Universal Perturbation attacks

<p>Recent research has established the possibility of deducing soft-biometric attributes such as age, gender and race from an individual’s face image with high accuracy. Many techniques have been proposed to ensure user privacy, such as visible distortions to the images, manipulation of the original image with new face attributes, face swapping etc. Though these techniques achieve the goal of user privacy by fooling face recognition models, they don’t help the user when they want to upload original images without visible distortions or manipulation. The objective of this work is to implement techniques to ensure the privacy of user’s sensitive or personal data in face images by creating minimum pixel level distortions using white-box and black-box perturbation algorithms to fool AI models while maintaining the integrity of the image, so as to appear the same to a human eye.</p><div><br></div>

Facial Privacy Preservation using FGSM and Universal Perturbation attacks

<p>Recent research has established the possibility of deducing soft-biometric attributes such as age, gender and race from an individual’s face image with high accuracy. Many techniques have been proposed to ensure user privacy, such as visible distortions to the images, manipulation of the original image with new face attributes, face swapping etc. Though these techniques achieve the goal of user privacy by fooling face recognition models, they don’t help the user when they want to upload original images without visible distortions or manipulation. The objective of this work is to implement techniques to ensure the privacy of user’s sensitive or personal data in face images by creating minimum pixel level distortions using white-box and black-box perturbation algorithms to fool AI models while maintaining the integrity of the image, so as to appear the same to a human eye.</p><div><br></div>

Deep Q-Learning-Based Neural Network with Privacy Preservation Method for Secure Data Transmission in Internet of Things (IoT) Healthcare Application

The healthcare industry is being transformed by the Internet of Things (IoT), as it provides wide connectivity among physicians, medical devices, clinical and nursing staff, and patients to simplify the task of real-time monitoring. As the network is vast and heterogeneous, opportunities and challenges are presented in gathering and sharing information. Focusing on patient information such as health status, medical devices used by such patients must be protected to ensure safety and privacy. Healthcare information is confidentially shared among experts for analyzing healthcare and to provide treatment on time for patients. Cryptographic and biometric systems are widely used, including deep-learning (DL) techniques to authenticate and detect anomalies, andprovide security for medical systems. As sensors in the network are energy-restricted devices, security and efficiency must be balanced, which is the most important concept to be considered while deploying a security system based on deep-learning approaches. Hence, in this work, an innovative framework, the deep Q-learning-based neural network with privacy preservation method (DQ-NNPP), was designed to protect data transmission from external threats with less encryption and decryption time. This method is used to process patient data, which reduces network traffic. This process also reduces the cost and error of communication. Comparatively, the proposed model outperformed some standard approaches, such as thesecure and anonymous biometric based user authentication scheme (SAB-UAS), MSCryptoNet, and privacy-preserving disease prediction (PPDP). Specifically, the proposed method achieved accuracy of 93.74%, sensitivity of 92%, specificity of 92.1%, communication overhead of 67.08%, 58.72 ms encryption time, and 62.72 ms decryption time.