Related papers: Inference Attacks for X-Vector Speaker Anonymizati…

With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that these models may leak…

Inference centers need more data to have a more comprehensive and beneficial learning model, and for this purpose, they need to collect data from data providers. On the other hand, data providers are cautious about delivering their datasets…

In this paper, a new mathematical formulation for the problem of de-anonymizing social network users by actively querying their membership in social network groups is introduced. In this formulation, the attacker has access to a noisy…

The growing reliance on large-scale speech data has made privacy protection a critical concern. However, existing anonymization approaches often degrade data utility, for example by disrupting acoustic continuity or reducing vocal…

Deep learning voice models are commonly used nowadays, but the safety processing of personal data, such as human identity and speech content, remains suspicious. To prevent malicious user identification, speaker anonymization methods were…

With advances seen in deep learning, voice-based applications are burgeoning, ranging from personal assistants, affective computing, to remote disease diagnostics. As the voice contains both linguistic and para-linguistic information (e.g.,…

Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we…

Anonymizing sensitive information in user text is essential for privacy, yet existing methods often apply uniform treatment across attributes, which can conflict with communicative intent and obscure necessary information. This is…

The risks of publishing privacy-sensitive data have received considerable attention recently. Several de-anonymization attacks have been proposed to re-identify individuals even if data anonymization techniques were applied. However, there…

Recent research has proposed approaches that modify speech to defend against gender inference attacks. The goal of these protection algorithms is to control the availability of information about a speaker's gender, a privacy-sensitive…

Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to…

There are currently two approaches to anonymization: "utility first" (use an anonymization method with suitable utility features, then empirically evaluate the disclosure risk and, if necessary, reduce the risk by possibly sacrificing some…

Speech pseudonymization aims at altering a speech signal to map the identifiable personal characteristics of a given speaker to another identity. In other words, it aims to hide the source speaker identity while preserving the…

This paper describes our ongoing work on security verification against inference attacks on data trees. We focus on infinite secrecy against inference attacks, which means that attackers cannot narrow down the candidates for the value of…

Voice anonymisation is used to conceal voice identity while preserving linguistic content. Even if anonymisation seems strong, non-timbral cues such as accent that remain post-anonymisation can help re-identification and reveal sensitive…

The increasing capabilities of deep neural networks for re-identification, combined with the rise in public surveillance in recent years, pose a substantial threat to individual privacy. Event cameras were initially considered as a…

While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary…

Machine Learning approaches to Natural Language Processing tasks benefit from a comprehensive collection of real-life user data. At the same time, there is a clear need for protecting the privacy of the users whose data is collected and…

Advances in imaging technologies, combined with inexpensive storage, have led to an explosion in the volume of publicly available neuroimaging datasets. Effective analyses of these images hold the potential for uncovering mechanisms that…

An automatic speaker verification system aims to verify the speaker identity of a speech signal. However, a voice conversion system could manipulate a person's speech signal to make it sound like another speaker's voice and deceive the…