No Intruder, no Validity: Evaluation Criteria for Privacy-Preserving Text Anonymization
For sensitive text data to be shared among NLP researchers and practitioners, shared documents need to comply with data protection and privacy laws. There is hence a growing interest in automated approaches for text anonymization. However, measuring such methods' performance is challenging: missing a single identifying attribute can reveal an individual's identity. In this paper, we draw attention to this problem and argue that researchers and practitioners developing automated text anonymization systems should carefully assess whether their evaluation methods truly reflect the system's ability to protect individuals from being re-identified. We then propose TILD, a set of evaluation criteria that comprises an anonymization method's technical performance, the information loss resulting from its anonymization, and the human ability to de-anonymize redacted documents. These criteria may facilitate progress towards a standardized way for measuring anonymization performance.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributePrivacy PreservingText AnonymizationSimilar Papers 제목 키워드 기반
Privacy-Preserving Co-synthesis Against Sensor-Actuator Eavesdropping Intruder
In this work, we investigate the problem of privacy-preserving supervisory control against an external passive intruder via co-synthesis of dynamic mask, edit function, and supervisor for opacity enforcement and requirem…
Privacy PreservingFaceLinkGen: Rethinking Identity Leakage in Privacy-Preserving Face Recognition with Identity Extraction
Transformation-based privacy-preserving face recognition (PPFR) aims to verify identities while hiding facial data from attackers and malicious service providers. Existing evaluations mostly treat privacy as resistance t…
Face RecognitionA Framework for Generating Valid Context-Specific Benchmarks through Expert Guidance
This paper presents an end-to-end approach for generating context-specific large language model (LLM) benchmark datasets by combining expert input with synthetic data generation. Existing benchmark construction methods o…
Synthetic Data GenerationPrivacy-Preserving Supervisory Control of Discrete-Event Systems via Co-Synthesis of Edit Function and Supervisor for Opacity Enforcement and Requirement Satisfaction
This paper investigates the problem of co-synthesis of edit function and supervisor for opacity enforcement in the supervisory control of discrete-event systems (DES), assuming the presence of an external (passive) intru…
Privacy PreservingA Control-Recoverable Added-Noise-based Privacy Scheme for LQ Control in Networked Control Systems
As networked control systems continue to evolve, ensuring the privacy of sensitive data becomes an increasingly pressing concern, especially in situations where the controller is physically separated from the plant. In t…
Privacy PreservingState Estimation