Executive Summary
Anthropic revealed that Russian hackers used Claude to automate malware evasion and that criminal groups increasingly target AI vendors' infrastructure, including an attempt to steal a pre-release Claude model.
What Happened
Anthropic reveals how criminal groups are increasingly targeting AI vendors' own infrastructure, including to steal a pre-release Claude model. The post Anthropic Says Russian Hackers Used Claude AI to Automate Malware Evasion appeared first on SecurityWeek .
Affected Products
- Anthropic Claude
Vulnerability / Attack Technique
AI-assisted malware evasion; targeting AI vendor infrastructure
Technical Mechanism
Attackers used Claude to automate changes that help malware evade detection, and separately targeted Anthropic's systems to steal a model.
AI Security Category
AI-assisted attack
Part of the AI-Assisted Attacks topic.
Relevant Frameworks
RealGround Analysis
AI vendors are both tools and targets. RealGround analysis: model weights are high-value assets that need protection like source code and secrets.
Recommended Controls
- Protect model weights with strict access control and monitoring
- Update detection for AI-assisted evasion techniques
Related RealGround Service
AI Agent SBOM and LLM Mapping · or start with the free AI Agent Security Scanner.
Sources
securityweek.com: https://www.securityweek.com/anthropic-says-russian-hackers-used-claude-ai-to-automate-malware-evasion/
Summary and analysis written by RealGround from the source above; last updated 2026-10-17.