Disrupting the first reported AI-orchestrated cyber espionage campaign \ Anthropic
anthropic.com · 1,419 words · saved by 9 readers
A report describing an a highly sophisticated AI-led cyberattack
Policy Disrupting the first reported AI-orchestrated cyber espionage campaign Nov 13, 2025 Read the report We recently argued that an inflection point had been reached in cybersecurity: a point at which AI models had become genuinely useful for cybersecurity operations, both for good and for ill. This was based on systematic evaluations showing cyber capabilities doubling in six months; we’d also been tracking real-world cyberattacks, observing how malicious actors were using AI capabilities. While we predicted these capabilities would continue to evolve, what has stood out to us is how quickl
saved by
- Janabel Xia
- Rikard Saqe
- Vincent Huang
- Neil Warren
- Jason Hausenloy
- Julian H
- mateus de sousa
- Will Anderson
- Andrew Dong
related reading
- Countering misuse of AI: September 2026 / Anthropicanthropic.com
- Detecting and preventing distillation attacks \ Anthropicanthropic.com
- Incident Report: unsanctioned agent behaviour during cyber testing | AISI Workaisi.gov.uk
- Claude Was Just Following Orderssubstack.com
- Strategic AI Sabotage: State Attacks on Advanced Systems' Developmenttwmstone.com
- When AI builds itself \ Anthropicanthropic.com
- Assessing Claude Mythos Preview’s cybersecurity capabilities \ Anthropicred.anthropic.com
- The End-State Fallacy: Where Is AI Security Headed?endstatefallacy.com
- Investigating three real-world incidents in our cybersecurity evaluations \ Anthropicanthropic.com
- Pre-deployment auditing can catch an overt saboteuralignment.anthropic.com
- Incidents | Rogue AI Trackerrogueaitracker.com
- Claude does cyber competitions \ Anthropicred.anthropic.com