Paper

When Agents Talk: Honeytokens under Shared Memory

Formal analysis of honeytoken limits when trusted agents and attackers share memory or policies.

HoneytokenApplicationIdentity

What we know

Formal analysis of honeytoken limits when trusted agents and attackers share memory or policies.

Evidence limits

The linked source supports a description of this resource, but this record does not yet document comparable outcomes or a specific critical review.

Reviewed: full text.

Full-text review · 2026-09-16

Design and scope

Formal analysis using total-variation bounds and repeated learning under shared memory.

Main finding

Shows that policies observable to trusted agents can leak how to distinguish honeytokens; proposes a private reference monitor.

Evidence limits

Results are theoretical and depend on assumptions about knowledge, repetition and response laws.

Sources and provenance

  1. When Agents Talk: Honeytokens under Shared Memory
    full-text · 2026-09-16

Reviewed: 2026-09-16. This record may change when new evidence is found.

RIS · BibTeX

Related resources

Open software

Canarytokens

Review: RepositoryCritical reading

Open project for creating decoy tokens that alert when someone uses them.

IdentityCloudHoneytoken