Malicious and Indirect

Classification

Domain

4. Malicious actors

Subdomain

4.0

Causal entity

—

Intent

—

Timing

—

How other frameworks describe this risk

• Dual-Use Capabilities Enable Malicious Use and Misuse of LLMs

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

• Malicious Use Risks

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

• Risks from malicious use

  International AI Safety Report 2025 (Bengio2025)

• Enabling malicious actors and harmful actions

  Navigating the Landscape of AI Ethics and Responsibility (Cunha2023)

• Malicious Use and Unleashing AI Agents

  Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements (Deng2023)

• Misuse risks

  Capabilities and Risks from Frontier AI (DSIT2023)

• Malicious Uses

  The Ethics of Advanced AI Assistants (Gabriel2024)

• Fine-tuning related (Ease of reconfiguring GPAI models)

  Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)

Other entries from Tang2025

• Scientific Domain of Agents Risk Category
• Chemical Risks Risk Sub-Category · 4.2
• Chemical Risks Additional evidence
• Biological Risks Risk Sub-Category · 4.2
• Biological Risks Additional evidence
• Radiological Risks Risk Sub-Category · 7.3
• Radiological Risks Additional evidence
• Physical (Mechanical ) Risks Risk Sub-Category · 7.3
• Physical (Mechanical ) Risks Additional evidence
• Information Science Risks Risk Sub-Category · 2.1
• Information Science Risks Additional evidence
• Emerging Tech Risk Sub-Category