Safety · Concept
Apothem-Optimal Neural Network Robustness Certifications
The apothem measure enables computation of robustness certifications in linear oracle calls, proving volume-optimal certifications are computationally intractable.
Forecast horizon
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
to · supports 3/10
Science of AI Evaluation Apothem-optimal robustness certifications provide more trustworthy safety guarantees for neural networks, advancing evaluation science.
+3 growth to · informs 2/10
Distributionally Robust Probabilistic Verification for AI Agents Apothem-optimal certifications provide tractable robustness bounds complementing probabilistic verification approaches for AI agents.
+2 growthSignal sources
Signal sources
Dated facts from primary sources in this direction.
US evaluation centre Jun 2025
In June 2025 the US AI Safety Institute was renamed the Center for AI Standards and Innovation (CAISI), pivoting toward security, standards and adversary-model assessment.
NIST → Frontier safeguards May 2025
Anthropic activated its ASL-3 deployment and security standard with Claude Opus 4 on 22 May 2025 — the first real-world trigger of a responsible-scaling tier, focused on blocking bio-weapon uplift.
Anthropic → Cross-border testing 2025
The International Network of AI Safety Institutes (launched Nov 2024) ran a third joint testing exercise focused on agentic AI systems across cyber and fraud strands.
European Commission — AI Office →