ThreatCluster

LLM-Generated Malware Shows Improvement, Still Ineffective for Deployment

First seen 2 Dec 2025, 18:33 UTC •Theregister •99% similarity •27

Article Content

Browse articles
ThreatCluster

Researchers at Netskope Threat Labs explored the capabilities of LLMs in generating malware. They successfully prompted both GPT-3.5-Turbo and GPT-4 to create malicious code, but the results were deemed too unreliable for operational use. As of now, LLM-generated malware is not ready for autonomous attacks.

ThreatCluster AI

Extracted Entities

1 / 2

Community

Browse all →

Tracked Entities in This Story

AWS Malware VMware Claude Code AI Claude Code AI Tool Gemini GPT-3.5-Turbo Gpt-4