arXiv (All)
open access
Faithful Dual-constrained Erasure for Robust LLM Safety Alignment
Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety alignment in Large Language Models (LLMs). However, recent studies reveal a persistent security risk: unlearned models remain highly vulnerable to retraining attacks, where suppressed maliciou
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
- Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs#1036827
- Faithful Dual-constrained Erasure for Robust LLM Safety Alignment#1136773
- Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models#1123051
- Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation#985042
- A Gravitational Interpretation of Safety Reversion under Fine-Tuning#1129317
Record · ID 1144246
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