arXiv (All)
open access
TRAP: Understanding and Mitigating Privacy Memorization in Language Models
Fine-tuning a language model on sensitive records can leave it able to reproduce them. We ask when this memorization arises and how to prevent it without knowing in advance which spans are sensitive. Our starting point is that most memorization scores and attacks share one statistical core: whether
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Beyond Memorization: Violating Privacy Via Inference with Large Language Models#281614
- Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs#973310
- Single-Layer MeMo as a Randomized Hamming-Kernel Classifier#1128827
- EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents#1129827
- Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots#781074
Record · ID 1116624
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive