RatHat Android trojan with AI-driven runtime behavior
Sep 16, 2026: Zimperium discovered RatHat, Android banking trojan making real-time API calls to Chinese LLM providers (DeepSeek, Qwen) during execution to adapt behavior. Trojan collects device state…
What happened
Sep 16, 2026: Zimperium discovered RatHat, Android banking trojan making real-time API calls to Chinese LLM providers (DeepSeek, Qwen) during execution to adapt behavior. Trojan collects device state (installed apps, security tools, screen content) and sends to LLM with prompt requesting optimal attack strategy. LLM responds with commands for credential harvesting, screen overlay injection, or SMS interception based on context. China-linked based on LLM provider selection and C2 infrastructure. Observed targeting banking apps across multiple regions.
RatHat Android trojan calls AI models at runtime to dynamically adapt malicious behavior based on device state
How it happened
Read the flow as text & sources
A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.
- 01 · Install malicious APK
User installs RatHat via phishing or third-party store
Source for step 1 - 02 · Collect device state
Trojan scans installed apps, security tools, screen content
Source for step 2 - 03 · Query LLM for strategy
Send device state to DeepSeek/Qwen with prompt requesting optimal attack approach
Source for step 3 - 04 · Execute LLM-directed attack
LLM responds with commands; trojan executes credential harvesting, overlay injection, or SMS interception
Source for step 4
Why it matters
Reported entry point: Sideloaded APK via phishing or malicious app stores. Reported impact: LLM responds with commands; trojan executes credential harvesting, overlay injection, or SMS interception; reported targets include Android users with banking apps; multiple regions; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.
What you can do
Protection & prevention
Install apps only from official stores; use mobile security solutions detecting runtime LLM API calls from apps; monitor for overlay attacks
Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.
Technical detailsTooling, impact & MITRE ATLAS
Attack context
- AI's role
- AI as operator
- Additional role
- LLM-generated malware
- Initial access
- Sideloaded APK via phishing or malicious app stores
Tooling as reported
AI products, models and artifacts
- DeepSeek (Chinese LLM)
- Qwen (Alibaba, Chinese LLM)
Other tooling
- Android banking trojan
- Screen overlay injection
- SMS interception
Targets and reported impact
- Targets / sectors
- Android users with banking apps; multiple regions
- Reported scale / exposure
- Unknown number of infections as of Sep 2026
- Target geography
- Multiple regions
Reported attribution
China-linked based on LLM provider selection
Structured attribution
- Actor
- Unknown
- Country
- China
- Motivation
- financially-motivated
- Attributed by
- Zimperium
- Attribution confidence
- medium
Detection rules
- Runtime LLM API monitoringGUIDANCE
Monitor Android apps for unexpected API calls to DeepSeek, Qwen, or other LLM providers; alert on overlay injection attempts
Activity timeline
- First seen
- 2026-09-01
- Last updated
- 2026-11-05
Updates
- 2026-09-16 — Zimperium
RatHat discovered making runtime LLM calls to adapt banking trojan behavior dynamically
Source defensive notes
Install apps only from official stores; use mobile security solutions detecting runtime LLM API calls from apps; monitor for overlay attacks
MITRE ATLAS
AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.
Android malware uses LLM at runtime to dynamically adapt attack behavior based on device state Source
Sources & research credit
1 sourceResearch by Zimperium · Zimperium
Zimperium analysis. First documented Android malware making runtime LLM API calls for adaptive behavior.
Record & downloads
- Source record name
- RatHat Android trojan with AI-driven runtime behavior
- Entry ID
- rathat-android-ai-runtime-2026-09
- Catalog review
- November 5, 2026
- Category
- adversary-use-of-ai
- AI involvement confidence
- confirmed