arXiv (OAI Expanded)
open access
BadEngram: Backdoor Attack on Gated Memory Components in LLMs
To expand open-weight models' capacity without proportionally increasing computation, recent language models incorporate gated parametric memories that retrieve learned values and inject them into intermediate representations. Despite these efficiency benefits, such modules create a distinct attack
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
- PSD: Pseudo Self-Distillation of Memory Representation Capabilities for LLM Agents#1049190
- Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models#1119421
- When Errors Become Memories: Causal Pathway Tracing in Multi-Turn Memory-Augmented LLMs#799419
- When Errors Become Memories: Causal Pathway Tracing in Multi-Turn Memory-Augmented LLMs#797996
- Mental Model Management: An Operator-Based Framework for LLM Memory#616617
Record · ID 1071263
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