In recent years, the proliferation of deep neural networks (DNNs) has revolutionized the field of artificial intelligence, enabling advancements in various domains. With the emergence of efficient learning techniques such as quantization and distributed learning, DNN systems have become increasingly accessible for deployment on edge devices. This accessibility brings significant benefits, including real-time inference on the edge, which mitigates communication latency, and on-device learning, which addresses privacy concerns and enables continuous improvement. However, the resource limitations of edge devices pose challenges in equipping them with robust safety protocols, making them vulnerable to various attacks. Two notable attacks that affect edge DNN systems are Bit-Flip Attacks (BFA) and architecture stealing attacks. BFA compromises the integrity of DNN models, while architecture stealing attacks aim to extract valuable intellectual property by reverse engineering the model's architecture. Furthermore, in Split Federated Learning (SFL) scenarios, where training occurs on distributed edge devices, Model Inversion (MI) attacks can reconstruct clients' data, and Model Extraction (ME) attacks can extract sensitive model parameters. This thesis aims to address these four attack scenarios and develop effective defense mechanisms. To defend against BFA, both passive and active defensive strategies are discussed. Furthermore, for both model inference and training, architecture stealing attacks are mitigated through novel defense techniques, ensuring the integrity and confidentiality of edge DNN systems. In the context of SFL, the thesis showcases defense mechanisms against MI attacks for both supervised and self-supervised learning applications. Additionally, the research investigates ME attacks in SFL and proposes countermeasures to enhance resistance against potential ME attackers. By examining and addressing these attack scenarios, this research contributes to the security and privacy enhancement of edge DNN systems. The proposed defense mechanisms enable safer deployment of DNN models on resource-constrained edge devices, facilitating the advancement of real-time applications, preserving data privacy, and fostering the widespread adoption of edge computing technologies.

Generative models in various domain such as images, speeches, and videos are beingdeveloped actively over the last decades and recent deep generative models are now capable of synthesizing multimedia contents are difficult to be distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation, Intellectual property theft(IP theft) and copyright infringement. One method to solve these threats is to embedded attributable watermarking in synthesized contents so that user can identify the user-end models where the contents are generated from. This paper investigates a solution for model attribution, i.e., the classification of synthetic contents by their source models via watermarks embedded in the contents. Existing studies showed the feasibility of model attribution in the image domain and tradeoff between attribution accuracy and generation quality under the various adversarial attacks but not in speech domain. This work discuss the feasibility of model attribution in different domain and algorithmic improvements for generating user-end speech models that empirically achieve high accuracy of attribution while maintaining high generation quality. Lastly, several experiments are conducted show the tradeoff between attributability and generation quality under a variety of attacks on generated speech signals attempting to remove the watermarks.

The purpose of an election is for the voice of the voters to be heard. All the participants in an election must be able to trust that the result of an election is actually the opinion of the people, unaltered by anything or anyone that may be trying to sway the vote. In the voting process, any "black boxes" or secrets can lead to mistrust in the system. In this thesis, an approach is developed for an electronic voting framework that is transparent, auditable, and scalable, making it trustworthy and usable for a wide-scale election. Based on my analysis, linkable ring signatures are utilized in order to preserve voter privacy while ensuring that a corrupt authenticating authority could not sway the vote. A hierarchical blockchain framework is presented to make ring signatures a viable signature scheme even when working with large populations. The solution is evaluated for compliance with secure voting requirements and scalability.

Infectious diseases spread at a rapid rate, due to the increasing mobility of the human population. It is important to have a variety of containment and assessment strategies to prevent and limit their spread. In the on-going COVID-19 pandemic, telehealth services including daily health surveys are used to study the prevalence and severity of the disease. Daily health surveys can also help to study the progression and fluctuation of symptoms as recalling, tracking, and explaining symptoms to doctors can often be challenging for patients. Data aggregates collected from the daily health surveys can be used to identify the surge of a disease in a community. This thesis enhances a well-known boosting algorithm, XGBoost, to predict COVID-19 from the anonymized self-reported survey responses provided by Carnegie Mellon University (CMU) - Delphi research group in collaboration with Facebook. Despite the tremendous COVID-19 surge in the United States, this survey dataset is highly imbalanced with 84% negative COVID-19 cases and 16% positive cases. It is tedious to learn from an imbalanced dataset, especially when the dataset could also be noisy, as seen commonly in self-reported surveys. This thesis addresses these challenges by enhancing XGBoost with a tunable loss function, ?-loss, that interpolates between the exponential loss (? = 1/2), the log-loss (? = 1), and the 0-1 loss (? = ∞). Results show that tuning XGBoost with ?-loss can enhance performance over the standard XGBoost with log-loss (? = 1).

Contact tracing has been shown to be effective in limiting the rate of spread of infectious diseases like COVID-19. Several solutions based on the exchange of random, anonymous tokens between users’ mobile devices via Bluetooth, or using users’ location traces have been proposed and deployed. These solutions require the user device to download the tokens (or traces) of infected users from the server. The user tokens are matched with infected users’ tokens to determine an exposure event. These solutions are vulnerable to a range of security and privacy issues, and require large downloads, thus warranting the need for an efficient protocol with strong privacy guarantees. Moreover, these solutions are based solely on proximity between user devices, while COVID-19 can spread from common surfaces as well. Knowledge of areas with a large number of visits by infected users (hotspots) can help inform users to avoid those areas and thereby reduce surface transmission. This thesis proposes a strong secure system for contact tracing and hotspots histogram computation. The contact tracing protocol uses a combination of Bluetooth Low Energy and Global Positioning System (GPS) location data. A novel and deployment-friendly Delegated Private Set Intersection Cardinality protocol is proposed for efficient and secure server aided matching of tokens. Secure aggregation techniques are used to allow the server to learn areas of high risk from location traces of diagnosed users, without revealing any individual user’s location history.