Semantics-Preserved Distortion for Personal Privacy Protection in Information Management
In recent years, machine learning - particularly deep learning - has significantly impacted the field of information management. While several strategies have been proposed to restrict models from learning and memorizing sensitive information from raw texts, this paper suggests a more linguistically-grounded approach to distort texts while maintaining semantic integrity. To this end, we leverage Neighboring Distribution Divergence, a novel metric to assess the preservation of semantic meaning during distortion. Building on this metric, we present two distinct frameworks for semantic-preserving distortion: a generative approach and a substitutive approach. Our evaluations across various tasks, including named entity recognition, constituency parsing, and machine reading comprehension, affirm the plausibility and efficacy of our distortion technique in personal privacy protection. We also test our method against attribute attacks in three privacy-focused assignments within the NLP domain, and the findings underscore the simplicity and efficacy of our data-based improvement approach over structural improvement approaches. Moreover, we explore privacy protection in a specific medical information management scenario, showing our method effectively limits sensitive data memorization, underscoring its practicality.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeConstituency ParsingFederated LearningMachine Reading ComprehensionManagementMemorizationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Reading ComprehensionSimilar Papers 제목 키워드 기반
Theoretically Principled Federated Learning for Balancing Privacy and Utility
We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arb…
Federated LearningBeyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection
Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to unintended privacy leakage. While adversa…
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exp…
Information ExtractionOn the Design of Privacy-Aware Cameras: a Study on Deep Neural Networks
In spite of the legal advances in personal data protection, the issue of private data being misused by unauthorized entities is still of utmost importance. To prevent this, Privacy by Design is often proposed as a soluti…
Towards Personalized Differentially Private Learning for Decentralized Local Graphs
Graph-structured data is increasingly generated and stored in decentralized environments, such as social platforms, mobile applications, and edge networks, where users maintain control over their local graph data. Howeve…
Graph Learning