conftrace_

pii leakage

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

privacy preservation (2) personally identifiable information (1) defensive strategy (1) model memorization (1) feature intervention (1) large language model (1) data security (1) circuit patching (1) information leakage (1) sparse autoencoder (1)

Papers

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing EACL 2026 PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders EMNLP 2025 Understanding PII Leakage in Large Language Models: A Systematic Survey IJCAI 2025