Not classified

GTIG AI Threat Tracker: distillation attacks, Gemini-calling HONESTCUE malware and AI-built phishing kits

Google's Q4 2025 tracker reports rising model-extraction attempts on Gemini, state actors using Gemini across the kill chain and first malware that fetches code from the Gemini API.

What happened

Google's Q4 2025 tracker reports rising model-extraction attempts on Gemini, state actors using Gemini across the kill chain and first malware that fetches code from the Gemini API.

Read the original sourceAdditional source: blog.googleAdditional source: bleepingcomputer.com

How it happened

Select a stage to explore its defenses
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
Read the flow as text & sources

A summary diagram derived from the entry fields, not a verified detailed sequence. Unknown steps remain explicit; an edge describes the reported relationship between steps.

  1. 01 · Reported initial access

    unknown

    Source for step 1
  2. 02 · Reported activity

    Google's Q4 2025 tracker reports rising model-extraction attempts on Gemini, state actors using Gemini across the kill chain and first malware that fetches code from the Gemini API.

    Source for step 2
  3. 03 · AI involvement

    Gemini, Gemini API, Lovable, shared-chat features of ChatGPT, Copilot, DeepSeek, Gemini and Grok · One API and New API gateways

    Source for step 3

Why it matters

Reported impact: the cited report does not establish a confirmed victim outcome; reported targets include Government; Defense; Finance; Technology and AI companies; Multiple sectors; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.

Read the original report

What you can do

Protection & prevention

Prevention guidance has not been recorded for this entry. Review the original report for available mitigations.

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance Additional source 2 Additional source 3
Technical detailsTooling, impact

Attack context

AI's role
AI as operator
Additional role
LLM-generated malware

Tooling as reported

AI products, models and artifacts

Targets and reported impact

Targets / sectors
Government; Defense; Finance; Technology and AI companies; Multiple sectors

Target geography was not captured by the Notion feed. Actor attribution is not used as a victim location.

Reported attribution

APT31, UNC795, APT41, APT42, UNC2970, UNC6418, Temp.HEX, UNC5356, IO actors; private-sector distillers

Structured attribution

Actor
APT31, UNC795, APT41, APT42, UNC2970, UNC6418, Temp.HEX, UNC5356, IO actors; private-sector distillers
Motivation
nation-state

Sources & research credit

3 sources

Research by unknown · Google Threat Intelligence Group

  1. cloud.google.com
  2. blog.google
  3. bleepingcomputer.com

Imported from the AI Threat Watch Notion feed (an automated daily scan); not yet editorially reviewed. Feed severity: High. Feed novelty: Evolution.

Record & downloads
Source record name
GTIG AI Threat Tracker: distillation attacks, Gemini-calling HONESTCUE malware and AI-built phishing kits
Entry ID
gtig-ai-threat-tracker-distillation-attacks-2026-02
Category
adversary-use-of-ai
AI involvement confidence
confirmed