Location-Based Recommendation Systems (LBRS) use device location data to suggest nearby hotels, restaurants, and points of interest. Since directly collecting location data from users can raise privacy concerns, there is growing interest in building recommendation systems based on Federated Learning (FL). Under FL, parameters of recommendation model learned on each user’s device are collected on a single server to build aggregated model. While FL does not raise privacy concerns about data collection since it does not collect user data directly, it may construct unfair models that repeatedly recommend specific locations. Although there are training methods to achieve fair recommendations that prevent such bias, they require more training epochs than usual. In FL, a malicious server can infer the original location data by continuously tracking a specific user’s parameter updates, and the inference accuracy increases proportionally with the number of training epochs. This means that achieving fair location recommendations in FL puts the original data at risk. In this paper, we design a novel parameter aggregation method to build fair and secure FL recommendation models. In the proposed aggregation method, users exchange parameters with each other before model aggregation to prevent malicious servers from inferring the original data. Even if a server (adversary) continuously tracks a specific user’s device, it cannot get parameters from the same user, thus preventing inference of the original location data. An experiment result demonstrated that the proposed method can reduce training time while maintaining the same accuracy as homomorphic encryption approach. © 2013 IEEE.

In recent years, to ensure a secure and stable food supply, aquaponics is gaining attention. The aquaponics is a novel agricultural system that integrates hydroponics and aquaculture and utilizes the nitrogen cycle facilitated by fish, plants, and bacteria without the need for pesticides. However, the management of the aquaponics is challenging because the nitrogen cycle should carefully be optimizes so as to maximize the production output of the fish and plants. Existing studies propose a system that automates the control of aquaponics systems, but does not support to automatically estimate fish and plant growth. Therefore, we propose a system that not only measures environmental conditions such as water temperature and pH, but also estimates the size of plants and fish to assess whether the condition of the field is appropriate for them or not. To continuously monitor the growth of fish, the proposed system includes a fish identification feature and an estimation feature of the length of each fish based on images captured by a stereo camera. Furthermore, in order to share the collected and estimated information among the fields, the proposed system is equipped with a secure data sharing system based on secure MQTT model. © 2025 IEEE.

Efforts towards the realization of smart cities are gaining increasing attention to improve the efficiency and comfort of social activities. The smart cities are built on the IoT systems that gather and analyze various sensor data from different parts of the city. The wireless sensor networks are essential for constructing the IoT systems but have various vulnerabilities (e.g., data tampering, eavesdropping) to the integrity of the sensor data due to the openness of wireless communication. The existing study proposes a system for detecting anomalies in the sensor data by verifying the correctness of the time-series characteristics. However, it is difficult for the existing system to detect attacks that tamper with the sensor data to simulate the realistic pattern of the time series. Therefore, in this study, we assume that sensor nodes physically close in proximity can generate sensor data with similar information, and propose a new method to ensure the integrity of the sensor data by enabling nodes participating in different sensor networks to collaborate with the adjacent nodes to verify the data. Even if multiple wireless sensor networks use different communication protocols (e.g., ZigBee, Thread), nearby sensor nodes can temporarily change the mode (e.g., BLE) to form a temporal network for data verification. Within the temporal network, each sensor node shares its data with adjacent nodes on the other networks, and compares time-series characteristics to ensure the integrity of the sensor data. © 2025 IEEE.

The Public Key Infrastructure (PKI) plays an essential role in securing Internet communications by enabling Certificate Authorities (CAs) to issue TLS certificates to web servers. These certificates enable browsers to authenticate web servers, though their expiration can disrupt website availability. To mitigate the problem, the Automated Certificate Management Environment (ACME) protocol automates certificate issuance and domain certification. However, Organization Validation (OV) certificate management is not automated because organization validation involves validating an organization's legal status and intent that are manually conducted, and are challenging to automate. This paper proposes an extended ACME protocol using Verifiable Credentials (VCs) to automate organization validation. VCs are digitally signed credentials issued by trusted authorities containing verifiable information, such as identity or educational qualifications. Reusing a previously issued VC for organization validation can pose significant risks by potentially enabling malicious actors to bypass the validation process. The proposed protocol solves this challenge by forcing a client requesting an OV certificate to obtain a short-lived VC after initiating the organization validation process, thereby limiting the reuse of VC and preventing unauthorized use. Our experimental results demonstrate that this protocol enhances security by preventing misuse of invalid VC while minimizing delays in certificate issuance. © 2025 IEEE.

The rise of the mobile era, especially with the availability of the internet, has significantly contributed to the growth of mobile banking, enhancing financial inclusion, particularly among underserved populations. However, reliance on basic mobile devices without advanced biometric security features exposes users to risks of financial fraud, unauthorized account access, and identity theft. This study introduces a lightweight speaker identification system tailored to improve the security of mobile banking in low-resource environments. By utilizing voice biometric authentication, the system confirms the user's identity through their voice at the end of each transaction, ensuring that only the authorized user can complete the transaction even if their Personal Identification Number (PIN) is compromised. The system combines advanced deep learning models, such as Whisper-large-v3 and Emphasized Channel Attention, Propagation, and Aggregation in Time Delay Neural Network (ECAPA-TDNN), to extract detailed voice features, including linguistic patterns and unique speaker traits, ensuring high accuracy and reliability in real-time identification. Additionally, liveness detection is integrated to defend against advanced spoofing, further enhancing system security. Evaluations on real-world data demonstrate the system's robust performance, achieving 99.59% accuracy, 99.62 % precision, and an Equal Error Rate (EER) of 0.0017, validating the system's practicality in constrained environments without requiring extensive computational resources. This solution provides a scalable and secure voice authentication method that is particularly beneficial for underserved communities, advancing both mobile banking security and financial inclusion. © 2025 IEEE.

Biometric verification is essential for secure identity verification and authentication during banking transactions using fingerprints, facial features, irises, and voices. Among these methods, voice biometrics is a promising alternative owing to its potential for robust and convenient user authentication. However, their effectiveness is significantly challenged by variations in the voice caused by different device configurations and environmental conditions. These variations can reduce the effectiveness of speaker identification and undermine the reliability of voice-based systems for securing online transactions. For an effective comparative solution, this study addresses these challenges by focusing on the difficulties posed by voice variations due to differences in device hardware, microphone quality, and environmental noise. Our approach employs machine-learning techniques using advanced speech enhancement methods to improve the consistency and accuracy of voice biometric verification across diverse devices. Specifically, we employ an adaptive filter model that enhances signal extraction, noise suppression, and predictive precision. Furthermore, our empirical demonstration showed that the adaptive filter significantly improved the accuracy of voice biometric systems by mitigating the impact of device-induced voice variations. In addition, we evaluate the performance of this model using a range of metrics. © 2024 IEEE.