MIT AI Risk Repository · Risk Category · 24.03.00
Malicious Uses
Description
"As AI assistants become more general purpose, sophisticated and capable, they create new opportunities in a variety of fields such as education, science and healthcare. Yet the rapid speed of progress has made it difficult to adequately prepare for, or even understand, how this technology can potentially be misused. Indeed, advanced AI assistants may transform existing threats or create new classes of threats altogether"
From The Ethics of Advanced AI Assistants (Gabriel2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Domain
- 4. Malicious actors
- Subdomain
- 4.0
- Causal entity
- Human
- Intent
- Intentional
- Timing
- Post-deployment
How other frameworks describe this risk
- Dual-Use Capabilities Enable Malicious Use and Misuse of LLMs
- Malicious Use Risks
- Risks from malicious use
- Enabling malicious actors and harmful actions
- Malicious Use and Unleashing AI Agents
- Misuse risks
- High-impact misuses and abuses beyond original purpose
- Fine-tuning related (Ease of reconfiguring GPAI models)
Other entries from Gabriel2024
- Capability failures
- Lack of capability for task
- Difficult to develop metrics for evaluating benefits or harms caused by AI assistants
- Safe exploration problem with widely deployed AI assistants
- Goal-related failures
- Misaligned consequentialist reasoning
- Specification gaming
- Goal misgeneralisation
- Deceptive alignment
- Offensive Cyber Operations (General)
- AI-Powered Spear-Phishing at Scale
- AI-Assisted Software Vulnerability Discovery