arXiv (All)
open access
How to Backdoor Image Knowledge Distillation
Knowledge distillation is widely used to transfer behavior from a large teacher model to a smaller student. It is often assumed to be safe when the teacher is clean, because classic backdoor attacks rely on poisoned labels and triggers in supervised training, whereas distillation trains the student
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
- Distillation as Probability Transport: Routed On-Policy Distillation#985698
- Distilling Directional Verification#1155932
- What Do Students Learn? A Feature-Level Analysis of Dark Knowledge#820494
- Contrastive On-Policy Distillation#1143849
- Retrospective Distillation Attribution via Normalized Response Similarity#1117080
Record · ID 984852
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