MIT AI Risk Repository · Risk Sub-Category · 47.01.03
Technical vulnerabilities (The risk of misalignment)
Category: Technical and operational risks
Description
"To assess whether an AI model is reliable or robust, it is crucial to consider whether the model is “aligned.” “Alignment” focuses on whether an AI model effectively operates in accordance with the goals established by its designers.238 A misaligned AI model may pursue some objectives, but not the intended ones. Therefore, misaligned AI models can malfunction and cause harm."
From Regulating under Uncertainty: Governance Options for Generative AI (G'sell2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Causal entity
- AI
- Intent
- Other
- Timing
- Post-deployment
Subdomain definition: AI systems acting in conflict with human goals or values, especially the goals of designers or users, or ethical standards. These misaligned behaviors may be introduced by humans during design and development, such as through reward hacking and goal misgeneralisation, or may result from AI using dangerous capabilities such as manipulation, deception, situational awareness to seek power, self-proliferate, or achieve other goals.
Real-world incidents in this subdomain
- Reinforcement Learning Reward Functions in Video Games
- Predictive Policing Program by Florida Sheriff’s Office Allegedly Violated Residents’ Rights and Targeted Children of Vulnerable Groups
- Image Classification of Battle Tanks
How other frameworks describe this risk
- Natural Language Underspecifies Goals
- Loss of control
- Loss of control
- Sudden loss of control
- AI leads to humans losing control of the future
- Risks from delegating decision-making power to misaligned AIs
- Risks from AIs developing goals and values that are different from humans
- Future AI systems might actively reduce human control
Other entries from G'sell2024
- Technical and operational risks
- Technical vulnerabilities (Robustness - unexpected behaviour)
- Technical vulnerabilities (Robustness - unexpected behaviour)
- Technical vulnerabilities (Robustness - vulnerability to jailbreaking
- Technical vulnerabilities (Robustness - vulnerability to jailbreaking
- Technical vulnerabilities (The risk of misalignment)
- Factually incorrect content (inaccuracies and fabricated sources)
- Factually incorrect content (inaccuracies and fabricated sources)
- Opacity (the black box problem)
- Opacity (industry opacity)
- Opacity (industry opacity)
- Ethical and social risks