Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 14 of 14 for “"Safeguarding privacy"”.
-
TEEKAP: A PRIVACY-PRESERVING DATA-SHARING PLATFORM USING TRUSTED EXECUTION ENVIRONMENT
Safeguarding privacy in data sharing is challenging. The main reason is that data owners lose control over their shared data once the data is passed to another party. In this dissertation, we propose TEEKap, a privacy-preserving data-sharing platform that enables data owners to regain control over …
-
PRIVACY-PRESERVING COLLABORATIVE MACHINE LEARNING USING HOMOMORPHIC ENCRYPTION
… is an emerging field with great potential for safeguarding privacy in machine learning (ML) applications. It enables computations to be performed on encrypted data without requiring decryption, thereby offering new possibilities for ML applications that demand data privacy, such as training …
-
Differentially-private Multiparty Clustering
… (ML) across diverse domains, the necessity of privacy-preserving techniques has become paramount. The Euclidean k-Means problem, a fundamental component of unsupervised learning, brings to light this privacy challenge, especially in federated contexts. Existing Federated approaches utilizing …
-
Intelligent Inside Threat Detection Framework Based on Digital Twin, Transformer Variant Models, and Transfer Learning
… efficient. To overcome challenges like data privacy and resource costs, we introduced FedITD, a Federated Parameter-Efficient Tuning (PETuning) framework with Federated Learning (FL) and Transfer Learning. This framework allows for decentralized model learning without data transmission, …
-
Privacy in the face of surveillance: Fourth Amendment considerations for facial recognition technology
… public places no longer have an expectation of privacy in anonymity. Real-time identification using facial recognition surveillance technology is not currently ready for successful employment by law enforcement or government agencies, but the speed with which the technology is being developed …
-
RESPONSIBLE AI GOVERNANCE: BALANCING THE GOALS OF BIAS MITIGATION AND PRIVACY PROTECTION THROUGH TRANSPARENCY
… between the goals of debiasing AI systems and safeguarding privacy. While the development and use of AI systems offer significant benefits, they also present serious risks, including data-driven bias that reinforces social inequalities and improper data handling that compromises privacy. …
-
A Robust Data Obfuscation Technique for Privacy Preserving Collaborative Filtering
Privacy is defined as the freedom from unauthorized intrusion. The availability of personal information through online databases, such as government records, medical records, and voters and #146; lists, pose a threat to personal privacy. The concern over individual privacy has led to the …
-
Federated Learning-based Privacy Protection Methods in Smart Healthcare Systems
… Working with personal health data brings new privacy and security challenges that require attention from the cybersecurity community. Clients would lose control over their data when employing centralised machine learning algorithms for data analysis. By handling data at the client end and …
-
HUMAN-CENTRIC ACOUSTICS: THE INTERPLAY OF OPPORTUNITIES AND SECURITY
… improving communication, monitoring health, or safeguarding privacy. This dissertation delves into the intricate interplay of these opportunities and the security challenges inherent in human-centric acoustics, advancing the field toward innovative and user-focused solutions. The contributions …
-
The protection of privacy and private information in the digital age: a comparative study of English and Thai law applying to individual media users
… processes may cause more harm to another’s privacy than traditional media. Despite the vast research on privacy invasions in the traditional media context, there is little analysis of whether privacy torts can offer an appropriate response to privacy concerns in light of the individual media …
-
Uncovering the Potential of Federated Learning: Addressing Algorithmic and Data-driven Challenges under Privacy Restrictions
… directly sharing sensitive data, ensuring privacy and robustness. This Ph.D. dissertation delves into the intricacies of federated learning, investigating the algorithmic and data-driven challenges of deep learning models in the presence of additive noise in this framework. The main …
-
Privacy-preserving seedbased data synthesis
… way as to maximize utility while simultaneously safeguarding privacy? This thesis proposes an answer to this question by re-framing the problem of sharing sensitive datasets as a data synthesis task. Specifically, we propose a framework to synthesize full data records in a privacy-preserving way …
-
Uncover the Power of Multipath : Detecting NLOS Drones Using Low-Cost WiFi Devices
… Consumer UAVs have become an ideal vector for privacy invasions due to their affordability, size, maneuverability, and their ability to stream live high-quality video. There is considerable proliferation of drones in both civil and military domains. Hence it is critical to detect invading …
-
Διασφάλιση ιδιωτικότητας σε προσωπικά δίκτυα με επίγνωση κατάστασης
Η διατριβή πραγματεύεται την διασφάλιση της ιδιωτικότητας σε Προσωπικά Δίκτυα με επίγνωση κατάστασης. Αρχικά αναλύονται το περιβάλλον εφαρμογής, οι γενικές αλλά και ειδικές απαιτήσεις ασφαλείας και ιδιωτικότητας, με βάση τα σενάρια χρήσης Προσωπικών Δικτύων και συνασπισμών Προσωπικών Δικτύων. Η …