AltaySec · ATLAS 2026.07
AML.T0062

Discover LLM Hallucinations

C · Explainer (cannot be honestly simulated in-browser) AML.TA0008 · Discovery

Description

Adversaries may prompt large language models and identify hallucinated entities. They may request software packages, commands, URLs, organization names, or e-mail addresses, and identify hallucinations with no connected real-world source. Discovered hallucinations provide the adversary with potential targets to Publish Hallucinated Entities. Different LLMs have been shown to produce the same hallucinations, so the hallucinations exploited by an adversary may affect users of other LLMs.

Honesty-tier rationale

Discovery mostly probes the structure of real deployments; only the concept can be shown against a mock endpoint.

Source

← Back to the matrix