arXiv (All)
open access
TRACER: Trace-Regularized Training Against Indirect Prompt Injection
Indirect prompt injection uses untrusted retrieved content, tool outputs, or agent messages to override an LLM's intended behavior. We show that defense robustness is channel-conditioned: the same attack succeeds 18% of the time as a follow-up message but 53% when placed in retrieved context. We pro
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
- Unread or Unenforced? Separating Representation from Enforcement Failure in Content Guards#1062079
- CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents#618505
- Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents#821523
- Runaway Reaction: When Benign Skills Compose into Malicious Behavior#1202362
- Runaway Reaction: When Benign Skills Compose into Malicious Behavior#1194330
Record · ID 1344956
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