相关论文: Personhood Credentials: Human-Centered Design Reco…
User interface personalization enhances digital efficiency, usability, and accessibility. However, in user-driven setups, limited support for identifying and evaluating worthwhile opportunities often leads to underuse. We explore a…
This paper introduces a novel privacy-preservation framework named PFID for LLMs that addresses critical privacy concerns by localizing user data through model sharding and singular value decomposition. When users are interacting with LLM…
Facial personalization faces challenges to maintain identity fidelity without disrupting the foundation model's prompt consistency. The mainstream personalization models employ identity embedding to integrate identity information within the…
Sensor-based interactive systems -- e.g., "smart" speakers, webcams, and RFID tags -- allow us to embed computational functionality into physical environments. They also expose users to real and perceived privacy risks: users know that…
Over the past 15 years, researchers have identified an increasing number of security mechanisms that are so unusable that the intended users either circumvent them or give up on a service rather than suffer the security. With hindsight, the…
User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet how to reliably leverage preference signals for answer generation remains under-explored. In practice, preferences can be noisy, incomplete, or…
While the Internet was conceived as a decentralized network, the most widely used web applications today tend toward centralization. Control increasingly rests with centralized service providers who, as a consequence, have also amassed…
The collection and release of street-level recordings as Open Data play a vital role in advancing autonomous driving systems and AI research. However, these datasets pose significant privacy risks, particularly for pedestrians, due to the…
Today's AI recommendation algorithms produce a human dilemma between euphoria and freedom. To elaborate, four ways that recommenders reshape experience are delineated. First, the human experience of convenience is tuned to euphoric…
Auditing plays a pivotal role in the development of trustworthy AI. However, current research primarily focuses on creating auditable AI documentation, which is intended for regulators and experts rather than end-users affected by AI…
AI-driven recommender systems are often perceived as personalization black boxes, limiting users' ability to understand how their data shapes content (information asymmetry) or to influence system behavior meaningfully (power asymmetry).…
Digital identity systems have the promise of efficiently facilitating access to services for a nation's citizens while increasing security and convenience. There are many possible system architectures, each with strengths and weaknesses…
Privacy directly concerns the user as the data owner (data- subject) and hence privacy in systems should be implemented in a manner which concerns the user (user-centered). There are many concepts and guidelines that support development of…
As users shift from interacting actively with devices with screens to interacting seamlessly with smart environments, novel models of user authentication will be needed to maintain the security and privacy of user data. To understand users'…
Identity federations operating in a business or consumer context need to prevent the collection of user data across trust service providers for legal and business case reasons. Legal reasons are given by data protection legislation. Other…
Identification within media, whether with real or fictional characters, significantly impacts users, shaping their behavior and enriching their social and emotional experiences. Immersive media, like video games, utilize virtual entities…
This document considers the counteracting requirements of privacy and accountability applied to identity management. Based on the requirements of GDPR applied to identity attributes, two forms of identity, with differing balances between…
Recommendation systems aim to predict users' feedback on items not exposed to them. Confounding bias arises due to the presence of unmeasured variables (e.g., the socio-economic status of a user) that can affect both a user's exposure and…
Usable and secure authentication on the web and beyond is mission-critical. While password-based authentication is still widespread, users have trouble dealing with potentially hundreds of online accounts and their passwords. Alternatives…
As software becomes more complex and assumes an even greater role in our lives, formal verification is set to become the gold standard in securing software systems into the future, since it can guarantee the absence of errors and entire…