Not classified

Microsoft detects LLM-obfuscated SVG phishing that hid code behind business terminology

An SVG credential-phishing lure used likely LLM-written code that encoded its payload as sequences of business words.

What happened

An SVG credential-phishing lure used likely LLM-written code that encoded its payload as sequences of business words.

Read the original sourceAdditional source: helpnetsecurity.comAdditional source: thehackernews.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

    An SVG credential-phishing lure used likely LLM-written code that encoded its payload as sequences of business words.

    Source for step 2
  3. 03 · AI involvement

    Unspecified LLM (code assessed as AI-generated)

    Source for step 3

Why it matters

Reported impact: the cited report does not establish a confirmed victim outcome; reported targets include 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
LLM-generated malware
Additional role
AI as operator

Tooling as reported

AI products, models and artifacts

  • Unspecified LLM (code assessed as AI-generated)

Targets and reported impact

Targets / sectors
Multiple sectors

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

Structured attribution

Motivation
cybercrime

Sources & research credit

3 sources

Research by unknown · Microsoft Threat Intelligence

  1. microsoft.com
  2. helpnetsecurity.com
  3. thehackernews.com

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

Record & downloads
Source record name
Microsoft detects LLM-obfuscated SVG phishing that hid code behind business terminology
Entry ID
microsoft-detects-llm-obfuscated-svg-phishing-2025-09
Category
adversary-use-of-ai
AI involvement confidence
vendor-asserted