arXiv (All)
open access
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should redistribute attention between trusted and untrusted tokens, enabling models to reason over untrusted conten
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
- Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol#1467432
- Autonomous Intelligent Agents for Natural-Language-Driven Web Execution with Integrated Security Assurance#196420
- Cloud in the crosshairs: exposing vulnerabilities in web-based management interfaces of open-source IaaS platforms#474095
- Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs#1201152
- Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory#1064897
Record · ID 1469327
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