Papers & Research

Anthropic analyzes 832 malicious AI accounts: medium- and high-risk attackers jump from 33% to 56% in six months

Original title:What we learned mapping a year’s worth of AI-enabled cyber threats

AI summary

Anthropic analyzed 832 banned malicious accounts between March 2025 and March 2026, mapping them to the MITRE ATT&CK framework. 67.3% used AI to write malware, and 6.5% used it for lateral movement. Over six months, the share of medium- and high-risk attackers rose from 33% to 56%. AI use for account discovery grew 8.9%, while AI-assisted phishing fell 8.6%. Traditional threat assessment based on the number of techniques or the platform (Claude Code, API, chat interface) no longer works, and the MITRE ATT&CK framework has yet to include such agent orchestration behaviors.

Key Takeaways

  • Anthropic analyzed 832 banned malicious accounts between March 2025 and March 2026,mapping them to…
  • 3% used AI to write malware,and 6.
  • 5% used it for lateral movement.
  • Over six months,the share of medium- and high-risk attackers rose from 33% to 56%.
  • AI use for account discovery grew 8.

Quick Facts

Published
Updated
Source
Anthropic:Research(发表成果 · 网页)
Category
Papers & Research
AI score
69
Read the original Read the full article at the original source
Why it matters

这份报告用一整年的真实案例揭示了AI攻击正从初始入侵转向深度潜伏,连MITRE ATT&CK框架都开始跟不上。安全从业者值得一读,它告诉你下一波威胁长什么样。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Anthropic analyzes 832 malicious AI accounts: medium- and high-risk attackers jump from 33% to 56% in six months. June 3, 2026. https://new.nat6.net/en/news/cmpxvzm7o00jqsliwbt1hnvae/

View all →