Risks from malicious use

Classification

Domain

4. Malicious actors

Subdomain

4.0

Causal entity

Human

Intent

Intentional

Timing

Other

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)

• 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)

• High-impact misuses and abuses beyond original purpose

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

Other entries from Bengio2025

• Harm to individuals through fake content Risk Sub-Category · 4.3
• Harm to individuals through fake content Additional evidence
• Harm to individuals through fake content Additional evidence
• Manipulation of public opinion Risk Sub-Category · 4.1
• Manipulation of public opinion Additional evidence
• Cyber offence Risk Sub-Category · 4.2
• Cyber offence Additional evidence
• Cyber offence Additional evidence
• Cyber offence Additional evidence
• Cyber offence Additional evidence
• Biological and chemical attacks Risk Sub-Category · 4.2
• Risks from malfunctions Risk Category