Related papers: The Privacy ZEBRA: Zero Evidence Biometric Recogni…
While specialized learning-based models have historically dominated image privacy prediction, the current literature increasingly favours adopting large Vision-Language Models (VLMs) designed for generic tasks. This trend risks overlooking…
We propose a general statistical inference framework to capture the privacy threat incurred by a user that releases data to a passive but curious adversary, given utility constraints. We show that applying this general framework to the…
The importance of security metrics can hardly be overstated. Despite the attention that has been paid by the academia, government and industry in the past decades, this important problem stubbornly remains open. In this survey, we present a…
Speech data carries a range of personal information, such as the speaker's identity and emotional state. These attributes can be used for malicious purposes. With the development of virtual assistants, a new generation of privacy threats…
Biometrics make human identification possible with a sample of a biometric trait and an associated database. Classical identification techniques lead to privacy concerns. This paper introduces a new method to identify someone using his…
The First VoicePrivacy Attacker Challenge is a new kind of challenge organized as part of the VoicePrivacy initiative and supported by ICASSP 2025 as the SP Grand Challenge It focuses on developing attacker systems against voice…
The exponential growth of collected, processed, and shared microdata has given rise to concerns about individuals' privacy. As a result, laws and regulations have emerged to control what organisations do with microdata and how they protect…
Privacy and data protection constitute core values of individuals and of democratic societies. There have been decades of debate on how those values -and legal obligations- can be embedded into systems, preferably from the very beginning of…
Attribute-driven privacy aims to conceal a single user's attribute, contrary to anonymisation that tries to hide the full identity of the user in some data. When the attribute to protect from malicious inferences is binary, perfect privacy…
This work proposes a novel privacy-preserving neural network feature representation to suppress the sensitive information of a learned space while maintaining the utility of the data. The new international regulation for personal data…
As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge emerges: the model is expected to distinguish between users to manage information flow appropriately.…
Recently, opportunities to transmit speech data to deep learning models executed in the cloud have increased. This has led to growing concerns about speech privacy, including both speaker-specific information and the linguistic content of…
Speaker embeddings are ubiquitous, with applications ranging from speaker recognition and diarization to speech synthesis and voice anonymisation. The amount of information held by these embeddings lends them versatility, but also raises…
Facial recognition technologies are implemented in many areas, including but not limited to, citizen surveillance, crime control, activity monitoring, and facial expression evaluation. However, processing biometric information is a…
Iris-based biometric identification is increasingly recognized for its significant accuracy and long-term stability compared to other biometric modalities such as fingerprints or facial features. However, all biometric modalities are highly…
We present a study of privacy attitudes and behaviors of people who are blind or low vision. Our study involved in-depth interviews with 21 US participants. The study explores their risk perceptions and also whether and how they go about…
Anonymisation has the goal of manipulating speech signals in order to degrade the reliability of automatic approaches to speaker recognition, while preserving other aspects of speech, such as those relating to intelligibility and…
With the rapidly increasing ability to collect and analyze personal data, data privacy becomes an emerging concern. In this work, we develop a new statistical notion of local privacy to protect each categorical data that will be collected…
This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework. The proposed framework explicitly learns a degradation…
We propose a practical methodology to protect a user's private data, when he wishes to publicly release data that is correlated with his private data, in the hope of getting some utility. Our approach relies on a general statistical…