相关论文: VirtualIdentity: Privacy-Preserving User Profiling
Numerous studies in the literature have already shown the potential of biometrics on mobile devices for authentication purposes. However, it has been shown that, the learning processes associated to biometric systems might expose sensitive…
A pseudonymisation technique based on Merkle trees is described in this paper. More precisely, by exploiting inherent properties of the Merkle trees as cryptographic accumulators, we illustrate how user-generated pseudonyms can be…
The authentication field is evolving towards mechanisms able to keep users continuously authenticated without the necessity of remembering or possessing authentication credentials. While existing continuous authentication systems have…
Transparency regarding the processing of personal data in online services is a necessary precondition for informed decisions on whether or not to share personal data. In this paper, we argue that privacy interfaces shall incorporate the…
Social media and user-generated content (UGC) are increasingly important features of journalistic work in a number of different ways. However, their use presents major challenges, not least because information posted on social media is not…
Virtual reality (VR) platforms enable a wide range of applications, however, pose unique privacy risks. In particular, VR devices are equipped with a rich set of sensors that collect personal and sensitive information (e.g., body motion,…
In this work, we propose a profile matching (or deanonymization) attack for unstructured online social networks (OSNs) in which similarity in graphical structure cannot be used for profile matching. We consider different attributes that are…
While most of humanity is suddenly on the net, the value of this singularity is hampered by the lack of credible digital identities: Social networking, person-to-person transactions, democratic conduct, cooperation and philanthropy are all…
Multi-modal retrieval-augmented generation (MRAG) systems retrieve visual evidence from large image corpora to ground the responses of large multi-modal models, yet the retrieved images frequently contain human faces whose identities…
Recent advances in large pretrained text-to-image models have shown unprecedented capabilities for high-quality human-centric generation, however, customizing face identity is still an intractable problem. Existing methods cannot ensure…
Global models are trained to be as generalizable as possible, with user invariance considered desirable since the models are shared across multitudes of users. As such, these models are often unable to produce personalized responses for…
As an emerging paradigm in digital identity, Decentralized Identity (DID) appears advantages over traditional identity management methods in a variety of aspects, e.g., enhancing user-centric online services and ensuring complete user…
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…
As usage of generative AI tools skyrockets, the amount of sensitive information being exposed to these models and centralized model providers is alarming. For example, confidential source code from Samsung suffered a data leak as the text…
Eye-tracking technology is being increasingly integrated into mixed reality devices. Although critical applications are being enabled, there are significant possibilities for violating user privacy expectations. We show that there is an…
In recent years, user-generated content (UGC) has become one of the major video types consumed via streaming networks. Numerous research contributions have focused on assessing its visual quality through subjective tests and objective…
Many video classification applications require access to personal data, thereby posing an invasive security risk to the users' privacy. We propose a privacy-preserving implementation of single-frame method based video classification with…
On the Internet large service providers tend to control the digital identities of users. These defacto identity authorities wield significant power over users, compelling them to comply with non-negotiable terms, before access to services…
This paper presents a privacy-preserving protocol for identity registration and information sharing in federated authentication systems. The goal is to enable Identity Providers (IdPs) to detect duplicate or fraudulent identity enrollments…
Deep learning-based face recognition (FR) systems pose significant privacy risks by tracking users without their consent. While adversarial attacks can protect privacy, they often produce visible artifacts compromising user experience. To…