Related papers: AGAPECert: An Auditable, Generalized, Automated, P…
Machine learning models are susceptible to a variety of attacks that can erode trust, including attacks against the privacy of training data, and adversarial examples that jeopardize model accuracy. Differential privacy and certified…
Attribute-based encryption is a form of encryption which offers the capacity to encrypt data such that it is only accessible to individuals holding a satisfactory configuration of attributes. As cloud and distributed computing become more…
Privacy leakage in AI-based decision processes poses significant risks, particularly when sensitive information can be inferred. We propose a formal framework to audit privacy leakage using abductive explanations, which identifies minimal…
In recent years, many countries have started enacting laws to safeguard privacy of personal data of their citizens collected and maintained by various enterprises through websites, mobile apps, and other means. It is imperative that the…
The growing utilization of Internet of Medical Things (IoMT) devices, including smartwatches and wearable medical devices, has facilitated real-time health monitoring and data analysis to enhance healthcare outcomes. These gadgets…
In this work, we introduce the private, anonymous, collateralizable commitments (PACCs) framework. PACCs allow any smart contract wallet holder to collateralize a claim, request, or commitment in general, in a private and anonymous manner.…
The black-box service model enables ML service providers to serve clients while keeping their intellectual property and client data confidential. Confidentiality is critical for delivering ML services legally and responsibly, but makes it…
Fintech provides technological services to increase operational efficiency in financial institutions, but traditional perimeter-based defense mechanisms are insufficient against evolving cyber threats like insider attacks, malware…
The rapid integration of IoT with edge computing has revolutionized various domains, particularly healthcare, by enabling real-time data sharing, remote monitoring, and decision-making. However, it introduces critical challenges, including…
With the growing need to comply with privacy regulations and respond to user data deletion requests, integrating machine unlearning into IoT-based federated learning has become imperative. Traditional unlearning methods, however, often lack…
As more and more data is collected for various reasons, the sharing of such data becomes paramount to increasing its value. Many applications ranging from smart cities to personalized health care require individuals and organizations to…
The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important…
Digital healthcare systems have revolutionized medical services, facilitating provider collaboration, enhancing diagnosis, and optimizing and improving treatments. They deliver superior quality, faster, reliable, and cost-effective…
In an era of heightened digital interconnectedness, businesses increasingly rely on third-party vendors to enhance their operational capabilities. However, this growing dependency introduces significant security risks, making it crucial to…
The integration of Fog Computing with Flying Ad-Hoc Networks (FANETs) offers promising capabilities for decentralized, low-latency intelligence in UAV-based applications. However, the distributed nature, mobility, and resource constraints…
Attributed Graph Clustering (AGC) is a fundamental unsupervised task that integrates structural topology and node attributes to uncover latent patterns in graph-structured data. Despite its significance in industrial applications such as…
This article describes how technical infrastructure developed by the nonprofit OpenMined enables external scrutiny of AI systems without compromising sensitive information. Independent external scrutiny of AI systems provides crucial…
Visual private information leakage is an emerging key issue for the fast growing applications of video understanding like activity recognition. Existing approaches for mitigating privacy leakage in action recognition require privacy labels…
We propose a new computationally efficient privacy-preserving identification framework based on layered sparse coding. The key idea of the proposed framework is a sparsifying transform learning with ambiguization, which consists of a…
Business process collaboration between independent parties can be challenging, especially if the participants do not have complete trust in each other. Tracking actions and enforcing the activity authorizations of participants via…