AnthropicPDF
Full report: Disrupting the first reported AI-orchestrated cyber espionage campaign
Excerpt
November 2025
anthropic.com
Changelog
November 17, 2025
● Updated language in the Executive Summary (p.3) to clarify our high confidence in our attribution of the espionage operation.
2
Executive summary
We have developed sophisticated safety and security measures to prevent the misuse of our AI models. While these measures are generally effective, cybercriminals and other malicious actors continually attempt to find ways around them. This report details a recent threat campaign we identified and disrupted, along with the steps we've t…
The opening of the report, shown for reference. The full report, with its figures and indicators, is published by Anthropic on assets.anthropic.com.
More from Anthropic3
- Countering misuse of AI: September 2026 / AnthropicAnthropic · Added 14 Oct
- Disrupting the first reported AI-orchestrated cyber espionage campaignAnthropic · Added 29 Apr
- b2a76c6f6992465c09a6f2fce282f6c0cea8c200.pdfAnthropic · Added 30 Aug 2025
On the same topics
- Retrohunting APT37: North Korean APT used VBA self decode technique to inject RokRatMalwarebytes · Published 5 Jan 2021
- Kazuar (Malware Family)Malpedia · Added 18 Oct
- Chinese Nation-State Hackers Target U.S in Operation TradeSecret, Report Claimseweek.com · Published 6 Apr 2017
- Taiwan High-Tech Ecosystem Targeted by Foreign APT Group:Medium · Published 10 Jun 2022
