arXiv (All)
open access
Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors
AI control protocols aim to get useful work from models that may be misaligned by monitoring their behaviour. One approach uses a second copy of the same model as the monitor. This avoids relying on a weaker reviewer the model could outsmart, but risks collusion: the model, now monitoring itself, ma
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
- Alignment via Training Against Probes Without Losing Monitorability#1143246
- Alignment via Training Against Probes Without Losing Monitorability#1136796
- The Agentic AI Framework (AAIF): a policy-enforced architecture for accountable and high-performance intrusion detection.#295441
- NovaFabric: Tamper-Evident, Replayable Evidence for Autonomous AI Agent Runs#1070072
- Adversarial Benchmarks and BenchDoor Attacks: Exploiting Benchmark Incentives for Backdoor Attacks#1403329
Record · ID 1423374
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