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 17 of 17 for “"Privacy Leakage"”.
-
Towards Understanding Privacy Leakage in Decentralized and Collaborative Learning
… monopolizing the ML ecosystem? What unique privacy and security risks arise from alternative ML orchestration system designs? Furthermore, how do these vulnerabilities and system failures inform our understanding of both how and what machines learn? This thesis attempts to explore these …
-
Neural Data Shaping and Evaluation via Mutual Information Estimation
… the scarcity of data that is publicly available. Privacy protection regulations such as HIPAA and GDPR and recent progress in information estimation literature motivate us to investigate the issue from an information theoretic perspective. In this thesis, we propose InfoShape, an encoder training …
-
Incentive mechanism design for mobile crowd sensing systems
… sensitive and private information, which causes privacy leakage for participants. Clearly, the power of crowd sensing could not be fully unleashed, unless workers are properly incentivized to participate via satisfactory rewards that effectively compensate their participation costs. Targeting the …
-
Detecting vulnerabilities of broadcast receivers in Android applications
… threats to its users. Current research about the privacy leakage in Android mostly focuses on Activity, Service and Content Providers. Little attention has been paid to the vulnerability of Broadcast Receiver, which is expected to assist inter-component collaboration and facilitate component …
-
Differential Privacy in Reinforcement Learning
… information, the security of policies and privacy preservation in reinforcement learning have given rise to widespread concerns. In addition, deep reinforcement learning policies parameterized by neural networks have been demonstrated to be vulnerable to adversarial attacks in supervised …
-
Group representation learning for group recommendation
… only group recommendation, but also to personal privacy when the users intend to conceal their personal preferences, but have participated in group decisions. To tackle these two problems, we propose and study DeepGroup – a deep learning approach for group recommendation with group implicit data. …
-
Vulnerability exploration and data protection in end-user applications
… such as identity theft, financial loss, and privacy leakage. Therefore, exploring potential vulnerabilities and protecting sensitive data in end-user applications are of great need and importance. In this dissertation, we explore the vulnerabilities in both end-user applications and end …
-
Synthetic Electronic Medical Record Generation using Generative Adversarial Networks
… Artificial data generation can help reduce privacy leakage for dataset owners as it is proven that de-identification methods are prone to re-identification attacks. We propose a novel approach we call Improved Correlation Capturing Wasserstein Generative Adversarial Network (SCorGAN) to …
-
Learning to Improve Clinical Decisions and AI Safety by Leveraging Structure
… techniques using gradient structure to mitigate privacy leakage. In this thesis, we develop methods on different medical modalities such as multivariate physiological signals of ICU patients, patient discharge summaries, biomedical scientific articles, radiology reports, chest radiography imaging …
-
Using Public and Private Blockchains for Secure Data Sharing and Analytics
… data is col- lected for various reasons. Due to privacy, and security concerns and regulatory compliance issues, the conditions under which the sharing occurs needs to be carefully specified and managed. Voter registration, financial compliance, healthcare management systems, insur- ance …
-
Privacy Attacks and Defenses under Security Threats in Machine Learning
… against threats in the real world, including privacy risks and security concerns. In terms of privacy risks, malicious users can steal the private information of other users or model owners, including recovering training data, inferring membership, and cloning the trained model without …
-
The two faces of mobile sensing
… would also spawn new threats to security and privacy. Exploring the dual character of mobile sensing is challenging. On one hand, while the commercialization of new mobile devices enlarges the design space, it is challenging to design effective mobile sensing systems, which use less or cheaper …
-
Hardware-Aided Privacy Protection and Cyber Defense for IoT
… by the development of these technologies, privacy concerns and security issues are two topics that deserve more attention. On one hand, as smart things continue to grow in their abilities to sense the physical world and capabilities to send information out through the Internet, they have …
-
Search over Encrypted Data in Cloud Computing
… data and applications into the cloud exposes a privacy leakage risk of the user data. As the growing awareness of data privacy, more and more users begin to choose proactive protection for their data in the cloud through data encryption. One major problem of data encryption is that it hinders …
-
Enable Intelligence on Billion Devices with Deep Learning
… due to the several critical challenges including privacy, efficiency, and performance.Conventional wisdom requires edge devices to transmit the data to cloud datacenters for training and inference. But moving a huge amount of data is prohibited by cost, high transmission delay, and privacy …
-
Android at risk: current threats stemming from unprotected local and external resources
… need to access such information and the privacy leakage risk involved. Unfortunately the design assumptions made while adapting Linux to cre- ate Android is not the only flaw of the latter. Specifically this work is also concerned with the security and privacy implications of using …