Imagen de Portada

A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xin, Rui, Mireshghallah, Niloofar, Li, Shuyue Stella, Duan, Michael, Kim, Hyunwoo, Choi, Yejin, Tsvetkov, Yulia, Oh, Sewoong, Koh, Pang Wei
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
por: Mireshghallah, Niloofar, et al.
Publicado: (2023)

Position: Privacy Is Not Just Memorization!
por: Mireshghallah, Niloofar, et al.
Publicado: (2025)

Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
por: Kim, Hyunwoo, et al.
Publicado: (2026)

PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases
por: Bae, Yubeen, et al.
Publicado: (2025)

Sanitize Your Responses: Mitigating Privacy Leakage in Large Language Models
por: Fu, Wenjie, et al.
Publicado: (2025)

Privacy-Preserving Instructions for Aligning Large Language Models
por: Yu, Da, et al.
Publicado: (2024)

Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
por: Chen, Wei-Ning, et al.
Publicado: (2024)

Contrastive Privacy: A Semantic Approach to Measuring Privacy of AI-based Sanitization
por: Bissias, George, et al.
Publicado: (2026)

Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
por: Naseh, Ali, et al.
Publicado: (2025)

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
por: Borkar, Jaydeep, et al.
Publicado: (2025)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
por: Meng, Jiayang, et al.
Publicado: (2025)

Textual Unlearning Gives a False Sense of Unlearning
por: Du, Jiacheng, et al.
Publicado: (2024)

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
por: Fu, Jie, et al.
Publicado: (2026)

One-shot Empirical Privacy Estimation for Federated Learning
por: Andrew, Galen, et al.
Publicado: (2023)

Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
por: Kassem, Aly M., et al.
Publicado: (2024)

Quantifying Privacy Leakage in Split Inference via Fisher-Approximated Shannon Information Analysis
por: Deng, Ruijun, et al.
Publicado: (2025)

Depth Gives a False Sense of Privacy: LLM Internal States Inversion
por: Dong, Tian, et al.
Publicado: (2025)

A False Sense of Privacy: Towards a Reliable Evaluation Methodology for the Anonymization of Biometric Data
por: Hanisch, Simon, et al.
Publicado: (2023)

The Hidden Cost of Correlation: Rethinking Privacy Leakage in Local Differential Privacy
por: Jayawardana, Sandaru, et al.
Publicado: (2025)

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
por: Hayes, Jamie, et al.
Publicado: (2024)

AirGapAgent: Protecting Privacy-Conscious Conversational Agents
por: Bagdasarian, Eugene, et al.
Publicado: (2024)

Evaluating Privacy Leakage in Split Learning
por: Qiu, Xinchi, et al.
Publicado: (2023)

Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions
por: Carpentier, Robin, et al.
Publicado: (2024)

InfoDecom: Decomposing Information for Defending Against Privacy Leakage in Split Inference
por: Deng, Ruijun, et al.
Publicado: (2025)

Analysis of Privacy Leakage in Federated Large Language Models
por: Vu, Minh N., et al.
Publicado: (2024)

Maximal $α$-Leakage for Quantum Privacy Mechanisms
por: Yang, Bo-Yu, et al.
Publicado: (2024)

Casper: Prompt Sanitization for Protecting User Privacy in Web-Based Large Language Models
por: Chong, Chun Jie, et al.
Publicado: (2024)

CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning
por: Wang, Weiqi, et al.
Publicado: (2025)

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
por: Ganev, Georgi, et al.
Publicado: (2025)

Computing Maximal Per-Record Leakage and Leakage-Distortion Functions for Privacy Mechanisms under Entropy-Constrained Adversaries
por: Wu, Genqiang, et al.
Publicado: (2026)

Residual-PAC Privacy: Automatic Privacy Control Beyond the Gaussian Barrier
por: Zhang, Tao, et al.
Publicado: (2025)

PrivTru: A Privacy-by-Design Data Trustee Minimizing Information Leakage
por: Gehring, Lukas, et al.
Publicado: (2025)

Observable Channels, Not Just Storage: Evaluating Privacy Leakage in LLM Agent Pipelines
por: Huang, Tao, et al.
Publicado: (2026)

EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics
por: Li, Shuyue Stella, et al.
Publicado: (2026)

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
por: Zhong, Peter Yong, et al.
Publicado: (2025)

Investigating Privacy Leakage in Dimensionality Reduction Methods via Reconstruction Attack
por: Lumbut, Chayadon, et al.
Publicado: (2024)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
por: Li, Na, et al.
Publicado: (2025)

Evaluating Differential Privacy on Correlated Datasets Using Pointwise Maximal Leakage
por: Saeidian, Sara, et al.
Publicado: (2025)

Differentially Private Learning Needs Better Model Initialization and Self-Distillation
por: Ngong, Ivoline C., et al.
Publicado: (2024)

An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
por: Yang, Hongjang, et al.
Publicado: (2026)