arXiv (All)
open access
AI Models Can Provably Hide Arbitrary Capabilities
Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions by constructing backdoor attacks that embed encrypted neural
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
- AI Models Can Provably Hide Arbitrary Capabilities#1291720
- Securing Deep Learning Hardware: A Survey of Side-Channel Vulnerabilities and Countermeasures#343393
- Towards One-for-All Robustness Across a Continuum of Threat Levels#924322
- Towards One-for-All Robustness Across a Continuum of Threat Levels#920091
- Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications#271871
Record · ID 1298424
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