arXiv (All)
open access
Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
The expansion of text-to-image diffusion models has raised concerns about harmful outputs, from fabricated depictions of public figures to sexually explicit imagery. To mitigate such risks, prior work has proposed concept erasure methods that aim to sever unwanted concepts from the model via fine-tu
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
- Compositional Concept Erasure in Text-to-Image Diffusion Models via Hierarchically Grounded Semantic Surgery#1216712
- When Are Concepts Erased From Diffusion Models?#1187231
- GRACE: Adaptive Concept Erasure with Geometry-Guided Retention in Diffusion Models#1070205
- VisualErase: Dual-Branch Visual Trajectory Redirection for Robust Concept Erasure in Text-to-Image Diffusion Models#1200651
- $\mathbf{S^2LM}$: Towards Semantic Steganography via Large Language Models#1325054
Record · ID 1199666
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