稻草人新闻RSS 聚合阅读

← 返回 🛡️ 网络安全

On Anthropic’s AI Misuse Report

Schneier on Security Bruce Schneier 5 小时前 www.schneier.com

On Anthropic’s AI Misuse Report

Earlier this month, Anthropic published a long report detailing all of the Claude misuses it detected. Daniel Meissler usefully summarized the report into 117 findings.

A few of the highlights:

  • AI agents increasingly handled reconnaissance, exploitation, data theft, propaganda production, surveillance workflows, and research while humans selected targets, set goals, and reviewed important outputs.
  • The report describes attackers using AI to industrialize credential theft, cloud compromise, phishing, vulnerability research, and the extraction of sensitive data from downstream organizations.
  • Influence operations used persistent agent memory, fake news sites, fabricated journalists, synthetic personas, political profiling, and large-scale multilingual content, although high content volume often produced little genuine engagement.
  • Surveillance and repression cases included automated dossiers, biometric and communications analysis, transnational targeting, coercive recruitment, and systems that continued operating locally after model access was revoked.
  • Biological and weapons cases show dual-use risk: AI supported advanced scientific and military work, but the report generally doesn’t establish completed biological weapons or operational battlefield deployment.

Tags: AI, reports

Posted on September 25, 2026 at 7:07 AM • 6 Comments

在原文站打开 ↗

Cloudflare Workers 每 3 分钟抓一批,9 批轮完最快约 27 分钟 · 点右上 ↻ 立刻全量抓一次