arXiv (All)
open access
Anchored or Drifting: What Recursive Self-Generation Reveals About Training Data
Large generative models are known to memorize their training data, posing severe privacy risks. Yet, current methods to detect training membership typically rely on the weak signals of a single forward pass. In this work, we find that training samples and unseen (held-out) data follow visibly differ
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
- Cocoon: A System Architecture for Differentially Private Training with Correlated Noises#1186368
- Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning#1247582
- Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Path#1105999
- Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails#1118707
- Generative Models with Privacy Guarantees: Enhancing Data Utility while Minimizing Risk of Sensitive Data Exposure#100493
Record · ID 1202131
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