Agent-security research intensity (share of cs.CR)
Attack surface · source: arXiv cs.CR submissions
What this measures
The share of new arXiv cryptography-and-security (cs.CR) papers that engage with AI agents, LLMs, prompt injection and tool use. A rising share signals the security research field is being pulled toward AI-agent threats, which is evidence the threat surface is intensifying.
Recent values
| Date | Value |
|---|---|
| 2026-11-21 | 0.408 |
| 2026-11-20 | 0.411 |
| 2026-11-18 | 0.407 |
| 2026-11-17 | 0.405 |
| 2026-11-16 | 0.406 |
| 2026-11-15 | 0.409 |
| 2026-11-14 | 0.418 |
| 2026-11-13 | 0.417 |
| 2026-11-12 | 0.424 |
| 2026-11-11 | 0.425 |
| 2026-11-10 | 0.429 |
| 2026-11-09 | 0.426 |
| 2026-11-08 | 0.434 |
| 2026-11-07 | 0.429 |
| 2026-11-05 | 0.429 |
| 2026-11-04 | 0.433 |
Part of the Data Pressure Index. History before the first live day is reconstructed from current-method inputs.