arXiv (All)
open access
CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering
Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that suppresses this behavior inside the model. Per model, a five-step recipe fits a residual-stream direction from paired episodes differing only in whethe
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
- CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering#1122221
- Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation#1154971
- Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations#1131120
- Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs#997322
- $D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals#1143782
Record · ID 1131771
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