Related papers: Rethinking Self-Sovereign Identity Principles: An …
Driven by digitization in society and industry, automating behavior in an autonomous way substantially alters industrial value chains in the smart service world. As processes are enhanced with sensor and actuator technology, they become…
Self-sovereign identity is a new identity management paradigm that allows entities to really have the ownership of their identity data and control their use without involving any intermediary. Blockchain is an enabling technology for…
Human-data interaction (HDI) presents fundamentally different challenges from traditional data management. HDI systems must meet latency, correctness, and consistency needs that stem from usability rather than query semantics; failing to…
In the forthcoming era of 6G networks, characterized by unprecedented data rates, ultra-low latency, and ubiquitous connectivity, effective management of Virtualized Network Functions (VNFs) is essential. VNFs are software-based…
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…
Disguised face identification (DFI) is an extremely challenging problem due to the numerous variations that can be introduced using different disguises. This paper introduces a deep learning framework to first detect 14 facial key-points…
Authentication with username and password is becoming an inconvenient process for the user. End users typically have little control over their personal privacy, and data breaches effecting millions of users have already happened several…
An identity system based secure overlay for the Internet is presented. This includes a primary root-of-trust in self-certifying identifiers. It presents a formalism for Autonomic Identifiers (AIDs) and Autonomic Namespaces (ANs). They are…
In representation learning, a common approach is to seek representations which disentangle the underlying factors of variation. Eastwood & Williams (2018) proposed three metrics for quantifying the quality of such disentangled…
Traditional machine learning relies on a centralized data pipeline, i.e., data are provided to a central server for model training. In many applications, however, data are inherently fragmented. Such a decentralized nature of these…
In semi-supervised learning (SSL) for enhancing the performance of graph neural networks (GNNs) with unlabeled data, introducing mutually independent decision factors for cross-validation is regarded as an effective strategy to alleviate…
AI is moving from domain-specific autonomy in closed, predictable settings to large-language-model-driven agents that plan and act in open, cross-organizational environments. As a result, the cybersecurity risk landscape is changing in…
Modern cloud and enterprise systems rely on identity-centric authorization, assuming that callers possessing valid credentials are safe to execute commands. The emergence of autonomous AI agents invalidates this assumption: agents can…
As Artificial Intelligence (AI) permeates many aspects of society, it brings numerous advantages while at the same time raising ethical concerns and potential risks, such as perpetuating inequalities through biased or discriminatory…
Multi-agent systems face a fundamental architectural flaw: agent identity is bound to network location. When agents migrate between providers, scale across instances, or federate across organizations, URI-based identity schemes break…
The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential…
The passing of the eIDAS amendment marks an important milestone for EU countries and changes how they must manage digital credentials for both public services and businesses. Italy has led in adopting eIDAS, first with CIE and SPID identity…
The enormous growth of the complexity of modern computer systems leads to an increasing demand for techniques that support the comprehensibility of systems. This has motivated the very active research field of formal methods that enhance…
Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. Such a setting severely limits their scalability in real-world…
Personal data related to a user's activities, preferences and services, is considered to be a valuable commodity not only for a wide range of technology-oriented companies like Google, Amazon and Apple but also for more traditional…