Security & Defense

Classification

Domain

4. Malicious actors

Subdomain

4.2 Cyberattacks, weapon development or use, and mass harm

Causal entity

Human

Intent

Intentional

Timing

Post-deployment

Subdomain definition: Using AI systems to develop cyber weapons (e.g., coding cheaper, more effective malware), develop new or enhance existing weapons (e.g., Lethal Autonomous Weapons or CBRNE), or use weapons to cause mass harm.

Real-world incidents in this subdomain

• 1 Dec 2025Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data
• 10 Oct 2025OpenAI ChatGPT Models Reportedly Jailbroken to Provide Chemical, Biological, and Nuclear Weapons Instructions
• 27 Aug 2025Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales
• 10 Jul 2025LAMEHUG Malware Reportedly Integrates Large Language Model for Real-Time Command Generation in a Purported APT28-Linked Cyberattack
• 5 Jun 2025Reported AI-Aided Development of Explosive Devices by Long Island Resident Michael Gann
• 17 May 2025AI Chatbot Allegedly Used to Research Explosive Materials in Palm Springs Fertility Clinic Bombing

How other frameworks describe this risk

• Business operations/infrastructure damage

  A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

• Violence/armed conflict

  A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

• Hazardous Biological and Chemical Technologies

  Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024)

• Warfare and Physical Harm

  Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024)

• Cyber offence

  International Scientific Report on the Safety of Advanced AI (Bengio2024)

• Dual use science risks

  International Scientific Report on the Safety of Advanced AI (Bengio2024)

• Biological and chemical attacks

  International AI Safety Report 2025 (Bengio2025)

• Cyber offence

  International AI Safety Report 2025 (Bengio2025)

Other entries from Allianz2018

• Economic Risk Category · 6.2
• Increased income disparity Risk Sub-Category · 6.2
• Markets monopolization Risk Sub-Category
• Political Risk Category · 4.1
• Biased influence through citizen screening and tailored propaganda Risk Sub-Category · 4.1
• Potential exploitation by totalitarian regimes Risk Sub-Category · 6.1
• Mobility Risk Category · 6.5
• Cyber security Risk Sub-Category
• Liability issues in case of accidents Risk Sub-Category · 6.5
• Healthcare Risk Category · 5.1
• Alteration of social relationships may induce psychological distress Risk Sub-Category · 5.1
• Social manipulation in elderly- and child-care Risk Sub-Category · 5.1