paper-with-me

홈 › Papers

Privacy-preserving Active Learning on Sensitive Data for User Intent Classification

2019-03-26 · Oluwaseyi Feyisetan, Thomas Drake, Borja Balle, Tom Diethe

Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance. However, it requires sending data to annotators for labeling. This presents a possible privacy leak when the training set includes sensitive user data. In this paper, we describe an approach for carrying out privacy preserving active learning with quantifiable guarantees. We evaluate our approach by showing the tradeoff between privacy, utility and annotation budget on a binary classification task in a active learning setting.

📄 PDF Abstract BibTeX arXiv:1903.11112

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningBinary ClassificationGeneral Classificationintent-classificationIntent ClassificationPrivacy Preserving

Similar Papers 제목 키워드 기반

Dynamic User-controllable Privacy-preserving Few-shot Sensing Framework

2025-08-06 · Ajesh Koyatan Chathoth, Shuhao Yu, Stephen Lee arxiv

User-controllable privacy is important in modern sensing systems, as privacy preferences can vary significantly from person to person and may evolve over time. This is especially relevant in devices equipped with Inertia…

Human Activity RecognitionContrastive Learning

Privacy-Preserving Matrix Factorization for Recommendation Systems using Gaussian Mechanism

2023-04-11 · Sohan Salahuddin Mugdho, Hafiz Imtiaz

Building a recommendation system involves analyzing user data, which can potentially leak sensitive information about users. Anonymizing user data is often not sufficient for preserving user privacy. Motivated by this, w…

Privacy PreservingRecommendation Systems

Towards Privacy-Preserving and Personalized Smart Homes via Tailored Small Language Models

2025-07-10 · Xinyu Huang, Leming Shen, Zijing Ma, Yuanqing Zheng

Large Language Models (LLMs) have showcased remarkable generalizability in language comprehension and hold significant potential to revolutionize human-computer interaction in smart homes. Existing LLM-based smart home a…

Privacy PreservingSmall Language Model

SensitiveNets: Learning Agnostic Representations with Application to Face Images

2019-02-01 · Aythami Morales, Julian Fierrez, Ruben Vera-Rodriguez, Ruben Tolosana

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…

Face RecognitionFairnessPrivacy PreservingRepresentation Learning

Designing Privacy-Preserving Visual Perception for Robot Navigation Based on User Privacy Preferences

2026-04-07 · Xuying Huang, Sicong Pan, Delphine Reinhardt, Maren Bennewitz arxiv

Visual navigation is a fundamental capability of mobile service robots, yet the onboard cameras required for such navigation can capture privacy-sensitive information and raise user privacy concerns. Existing approaches …

Visual NavigationRobot Navigation