Related papers: Data Guard: A Fine-grained Purpose-based Access Co…
Deep learning models have achieved remarkable success in computer vision but still rely heavily on large-scale labeled data and tend to overfit when data is limited or distributions shift. Data augmentation -- particularly mask-based…
We propose WedgeChain, a data store that spans both edge and cloud nodes (an edge-cloud system). WedgeChain consists of a logging layer and a data indexing layer. In this study, we encounter two challenges: (1) edge nodes are untrusted and…
The ability to enforce robust and dynamic access controls on cloud-hosted data while simultaneously ensuring confidentiality with respect to the cloud itself is a clear goal for many users and organizations. To this end, there has been much…
As societal challenges grow more complex, access to data for public interest use is paradoxically becoming more constrained. This emerging data winter is not simply a matter of scarcity, but of shrinking legitimate and trusted pathways for…
The Cloud has become a new Information Technology(IT) model for delivering resources such as computing and storage to customers on demand, it provides both high flexibility and resources use. However we are gaining these advantages at the…
Enterprises increasingly rely on cloud-based applications to process highly sensitive data artifacts. Although cloud adoption improves agility and scalability, it also introduces new security challenges such as expanded attack surfaces, a…
Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable…
We introduce a new notion of neighboring databases for coverage problems such as Max Cover and Set Cover under differential privacy. In contrast to the standard privacy notion for these problems, which is analogous to node-privacy in…
Data warehousing is continuously gaining importance as organizations are realizing the benefits of decision oriented data bases. However, the stumbling block to this rapid development is data quality issues at various stages of data…
Role-Based Access Control (RBAC) struggles to adapt to dynamic enterprise environments with documents that contain information that cannot be disclosed to specific user groups. As these documents are used by LLM-driven systems (e.g., in…
Wearable devices can offer services to individuals and the public. However, wearable data collected by cloud providers may pose privacy risks. To reduce these risks while maintaining full functionality, healthcare systems require solutions…
Sensor technologies have evolved to a point where it is now practical to monitor products along the supply chain. The collected data can be stored in a decentralized way using blockchain technology. However, ensuring the reliability of the…
Cloud platform came into existence primarily to accelerate IT delivery and to promote innovation. To this point, it has performed largely well to the expectations of technologists, businesses and customers. The service aspect of this…
Data mining is a new concept & an exploration and analysis of large data sets, in order to discover meaningful patterns and rules. Many organizations are now using the data mining techniques to find out meaningful patterns from the…
Data lakes enable the training of powerful machine learning models on sensitive, high-value medical datasets, but also introduce serious privacy risks due to potential leakage of protected health information. Recent studies show adversaries…
In this research project, we investigate an alternative to the standard cloud-centralized data architecture. Specifically, we aim to leave part of the application data under the control of the individual data owners in decentralized…
Social platforms have revolutionized information sharing, but also accelerated the dissemination of harmful and policy-violating content. To ensure safety and compliance at scale, moderation systems must go beyond efficiency and offer…
Machine learning (ML) is vulnerable to inference (e.g., membership inference, property inference, and data reconstruction) attacks that aim to infer the private information of training data or dataset. Existing defenses are only designed…
As Large Language Models (LLMs) continue to be increasingly applied across various domains, their widespread adoption necessitates rigorous monitoring to prevent unintended negative consequences and ensure robustness. Furthermore, LLMs must…
In Europe and indeed worldwide, the General Data Protection Regulation (GDPR) provides protection to individuals regarding their personal data in the face of new technological developments. GDPR is widely viewed as the benchmark for data…