Related papers: Security and Privacy Implications of Middlebox Coo…
Centralized systems in the Internet of Things---be it local middleware or cloud-based services---fail to fundamentally address privacy of the collected data. We propose an architecture featuring secure multiparty computation at its core in…
Our previous experience building systems for middlebox chain composition and scaling in software-defined networks has revealed that existing mechanisms of flow annotation commonly do not survive middlebox-traversals, or suffer from extreme…
High-latency anonymous communication systems prevent passive eavesdroppers from inferring communicating partners with certainty. However, disclosure attacks allow an adversary to recover users' behavioral profiles when communications are…
Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data as well as the resulting decisions, several ethical concerns need to be addressed for the…
In the Internet of Things and smart environments data, collected from distributed sensors, is typically stored and processed by a central middleware. This allows applications to query the data they need for providing further services.…
The cloud infrastructure must provide security for High-Performance Computing (HPC) applications of sensitive data to execute in such an environment. However, supporting security in the communication infrastructure of today's public cloud…
Secure Multiparty Computation (MPC) can improve the security and privacy of data owners while allowing analysts to perform high quality analytics. Secure aggregation is a secure distributed mechanism to support federated deep learning…
Differential privacy protects an individual's privacy by perturbing data on an aggregated level (DP) or individual level (LDP). We report four online human-subject experiments investigating the effects of using different approaches to…
Distributed computing enables scalable machine learning by distributing tasks across multiple nodes, but ensuring privacy in such systems remains a challenge. This paper introduces a novel private coded distributed computing model that…
Federated learning systems increasingly rely on diverse network topologies to address scalability and organizational constraints. While existing privacy research focuses on gradient-based attacks, the privacy implications of network…
As Agentic AI gain mainstream adoption, the industry invests heavily in model capabilities, achieving rapid leaps in reasoning and quality. However, these systems remain largely confined to data silos, and each new integration requires…
Decentralized optimization is increasingly popular in machine learning for its scalability and efficiency. Intuitively, it should also provide better privacy guarantees, as nodes only observe the messages sent by their neighbors in the…
Secure Multi-Party Computation (MPC) enables collaborative analytics without exposing private data. However, OLAP queries under MPC remain prohibitively slow due to oblivious execution and padding of intermediate results with filler tuples.…
Ensuring equitable privacy experiences remains a challenge, especially for marginalised and vulnerable populations (MVPs) who often hesitate to participate or use digital services due to concerns about the privacy of their sensitive…
Cooperative spectrum sensing, despite its effectiveness in enabling dynamic spectrum access, suffers from location privacy threats, merely because secondary users (SUs)' sensing reports that need to be shared with a fusion center to make…
One of the main challenges faced by a user today is protecting their privacy, especially during widespread surveil- lance. This led to the development of privacy infrastructures whose main purpose is to guarantee users privacy. However,…
Distributed computing frameworks such as MapReduce have become essential for large-scale data processing by decomposing tasks across multiple nodes. The multi-access distributed computing (MADC) model further advances this paradigm by…
Differential privacy (DP) is a formal privacy framework that enables training machine learning (ML) models while protecting individuals' data. As pointed out by prior work, ML models are part of larger systems, which can lead to so-called…
Many commonly used learning algorithms work by iteratively updating an intermediate solution using one or a few data points in each iteration. Analysis of differential privacy for such algorithms often involves ensuring privacy of each step…
The Model Context Protocol (MCP) has emerged as a de facto standard for integrating Large Language Models with external tools, yet no formal security analysis of the protocol specification exists. We present the first rigorous security…