paper-with-me

Papers

IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization

2024-07-03 · Ahmed Frikha, Nassim Walha, Krishna Kanth Nakka, Ricardo Mendes, Xue Jiang, Xuebing Zhou

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.

📄 PDF Abstract BibTeX arXiv:2407.02956

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeText Anonymization

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

The Impact of Speech Anonymization on Pathology and Its Limits

2024-04-11 · Soroosh Tayebi Arasteh, Tomas Arias-Vergara, Paula Andrea Perez-Toro, Tobias Weise 외

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 anonymization

Diff-Privacy: Diffusion-based Face Privacy Protection

2023-09-11 · Xiao He, Mingrui Zhu, Dongxin Chen, Nannan Wang 외

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…

DenoisingScheduling

Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach

2024-09-01 · Wenjun Huang, Yang Ni, Arghavan Rezvani, Sungheon Jeong 외

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 Estimation

CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

2020-05-19 · CVPR 2020 6 · Maxim Maximov, Ismail Elezi, Laura Leal-Taixé

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 Anonymization

Fair Play for Individuals, Foul Play for Groups? Auditing Anonymization's Impact on ML Fairness

2025-05-12 · Héber H. Arcolezi, Mina Alishahi, Adda-Akram Bendoukha, Nesrine Kaaniche

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