相关论文: Tau-Eval: A Unified Evaluation Framework for Usefu…

Process mining techniques enable analysts to identify and assess process improvement opportunities based on event logs. A common roadblock to process mining is that event logs may contain private information that cannot be used for analysis…

The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict between authorship verification and privacy preservation. Standard anonymization techniques often…

Removing personally identifiable information (PII) from texts is necessary to comply with various data protection regulations and to enable data sharing without compromising privacy. However, recent works show that documents sanitized by…

The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker. In this paper, we present a flexible pseudo-speaker selection technique as a baseline for the first VoicePrivacy…

Anonymous communication networks have emerged as crucial tools for obfuscating communication pathways and concealing user identities. However, their practical deployments face significant challenges, including susceptibility to artificial…

While previous works on privacy-preserving serial data publishing consider the scenario where sensitive values may persist over multiple data releases, we find that no previous work has sufficient protection provided for sensitive values…

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…

Current LLM-based frameworks for text anonymization usually rely on remote API services from powerful LLMs, which creates an inherent privacy paradox: users must disclose the raw data to untrusted third parties for guaranteed privacy…

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…

System logs constitute valuable information for analysis and diagnosis of system behavior. The size of parallel computing systems and the number of their components steadily increase. The volume of generated logs by the system is in…

Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In…

Current Large Language Models (LLMs) cannot support users to precisely balance privacy protection and output performance during individual consultations. We introduce Adanonymizer, an anonymization plug-in that allows users to control this…

LLM agents increasingly draft messages on behalf of users, yet users routinely overshare sensitive information and disagree on what counts as private. Existing systems support only suppression (omitting sensitive information) and…

Decentralized systems can be more resistant to operator mischief than centralized ones, but they are substantially harder to develop, deploy, and maintain. This cost is dramatically reduced if the decentralized part of the system can be…

To send encrypted emails, users typically need to create and exchange keys which later should be manually authenticated, for instance, by comparing long strings of characters. These tasks are cumbersome for the average user. To make more…

The need for privacy-preserving analytics is higher than ever due to the severity of privacy risks and to comply with new privacy regulations leading to an amplified interest in privacy-preserving techniques that try to balance between…

Despite the successes of language models, their evaluation remains a daunting challenge for new and existing tasks. We consider the task of text simplification, commonly used to improve information accessibility, where evaluation faces two…

Private function evaluation is a task that aims to obtain the output of a function while keeping the function secret. So far its quantum analogue has not yet been articulated. In this study, we initiate the study of quantum private function…

Most existing anonymization work has been done on static datasets, which have no update and need only one-time publication. Recent studies consider anonymizing dynamic datasets with external updates: the datasets are updated with record…

Evaluating the usefulness of data before purchase is essential when obtaining data for high-quality machine learning models, yet both model builders and data providers are often unwilling to reveal their proprietary assets. We present…