Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents
arXiv 2604.11839•a076afd6315e494d37628249db1513dd7fa7ebae76ff238c3c221c7efdd04bec
AI securityCAN bus encryptionFHELLAMA-3LLM privacyLLM watermarkingLLM-RedactorSIR-BenchTimeMarkautomotive securityautonomous agentscapability governancecapability overprovisioningforensics benchmarkinghomomorphic encryptionincident responseleast privilegelightweight cryptolocal inferenceprivacy-preserving inference post-quantumprompt redactionprovable watermarksafety classifiersandboxingtime watermarking
Paper metadata
- arXiv ID
- 2604.11839
- Version
- Not specified by this published record
- Category
- Computer Science — Cryptography and Security (cs.CR)
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
Evidence and limitations
- Source ID
- arxiv_cs_cr
- Record identifier
- a076afd6315e494d37628249db1513dd7fa7ebae76ff238c3c221c7efdd04bec
- Enrichment time
- 2026-04-15T07:23:35Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.