Gpt-5.4 Mini

Platform

Threat entity extracted from intelligence sources

Frequency

6

occurrences

First Seen

July 1, 2026

Last Seen

July 29, 2026

Overview

Recent Events

Relationships

The full threat graph for this incident is free in the 7-day Starter trial.

Create free account

No card · 30 seconds

See everything included

Related Clusters (3)

DeepKeep Reveals InkJect: New Visual Prompt Injection Vulnerability in AI Models

Jul 1·4 sources

Microsoft Unveils Project Perception to Combat AI-Powered Cyber Threats

Jul 28·11 sources

Microsoft Launches MAI-Cyber-1-Flash for Cybersecurity Workflows

Jul 28·5 sources

Related Articles (6)

Microsoft introduces its own AI model for cybersecurity

Heise.De·Jul 29

Microsoft has unveiled Project Perception

Mezha.Ua·Jul 28

Microsoft's new cyber model handles most MDASH work, but its top score still uses GPT

Deepkeep Exposes Inkject A New Visual Prompt Injection Vulnerability That Bypasses Guardrails In Leading Ai Models 302815702

www.prnewswire.com·Jul 1

DeepKeep Exposes 'InkJect,' a New Visual Prompt Injection Vulnerability that Bypasses ...

Morningstar·Jul 1

1 / 2

Related Entities

Zero-day Exploit Anthropic OpenAI DeepKeep Israel Claude Sonnet 4.6 Gpt-5.3 Codex Windows MAI-Code-1-Flash MAI-Cyber-1-Flash MAI-Thinking-1 Azure AI Foundry