# Databricks reports fewer missed binary malware detections with expert profiles

_Published Friday, October 16, 2026 at 12:28 PM EDT · Security, AI · Latest · Tier 2 — Notable_

![Databricks reports fewer missed binary malware detections with expert profiles — Primary](https://www.databricks.com/sites/default/files/2026-10/Gemini_Generated_Image_7h8l8a7h8l8a7h8l.jpeg)

Databricks reported that adding expert-written capability profiles to prompts reduced detection failures among seven budget AI models from 50% to 4% in tests of malicious binaries packaged as npm modules. The profiles encode attack techniques as weighted conditions applied to static scanner evidence.

The experiment covered ten crafted payloads and 70 model-payload tests in the budget tier. Profiles recovered 32 of 35 initial detection failures, but three remained below the escalation threshold. Failures at the stricter malicious-verdict threshold fell from 73% to 34%.

## Sources

- [Databricks](https://www.databricks.com/blog/closing-binary-blind-spot-domain-knowledge-injection-llm-malware-triage-npm-packages)

---
Canonical: https://techandbusiness.org/newswire/LvYselkJQpwtIYxD9px4GX
Published: 2026-10-16T16:28:54.178Z
Story chronology: 2026-10-16T15:37:00.000Z
Retrieved: 2026-10-16T19:07:08.551Z
Publisher: Tech & Business (techandbusiness.org)