IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
In this work, we address the problem of text anonymization where the goal is to prevent adversaries from correctly inferring private attributes of the author, while keeping the text utility, i.e., meaning and semantics. We propose IncogniText, a technique that anonymizes the text to mislead a potential adversary into predicting a wrong private attribute value. Our empirical evaluation shows a reduction of private attribute leakage by more than 90% across 8 different private attributes. Finally, we demonstrate the maturity of IncogniText for real-world applications by distilling its anonymization capability into a set of LoRA parameters associated with an on-device model. Our results show the possibility of reducing privacy leakage by more than half with limited impact on utility.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeText AnonymizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The Impact of Speech Anonymization on Pathology and Its Limits
Integration of speech into healthcare has intensified privacy concerns due to its potential as a non-invasive biomarker containing individual biometric information. In response, speaker anonymization aims to conceal pers…
DiagnosticFairnessSpeaker anonymizationDiff-Privacy: Diffusion-based Face Privacy Protection
Privacy protection has become a top priority as the proliferation of AI techniques has led to widespread collection and misuse of personal data. Anonymization and visual identity information hiding are two important faci…
DenoisingSchedulingRecoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach
Human pose estimation (HPE) is crucial for various applications. However, deploying HPE algorithms in surveillance contexts raises significant privacy concerns due to the potential leakage of sensitive personal informati…
Pose EstimationCIAGAN: Conditional Identity Anonymization Generative Adversarial Networks
The unprecedented increase in the usage of computer vision technology in society goes hand in hand with an increased concern in data privacy. In many real-world scenarios like people tracking or action recognition, it is…
Action RecognitionDe-identificationDiversityFace AnonymizationFair Play for Individuals, Foul Play for Groups? Auditing Anonymization's Impact on ML Fairness
Machine learning (ML) algorithms are heavily based on the availability of training data, which, depending on the domain, often includes sensitive information about data providers. This raises critical privacy concerns. A…
Fairness