arXiv (All)
open access
Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models
Safety heads are lightweight classifiers attached to pretrained language models for flagging harmful inputs before generation. Their empirical detection performance has been studied, but their formal robustness properties remain largely unexplored. We ask when a State Space Model (SSM)-based safety
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
- DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment#1345188
- Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines#798229
- Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines#796816
- Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?#985694
- Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers#1324431
Record · ID 1187167
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