MIT AI Risk Repository · Risk Sub-Category · 62.15.03
Fine-tuning related (Ease of reconfiguring GPAI models)
Category: Model Development
Description
"GPAI models are often easily reconfigured for various use cases or have competencies beyond the intended use [78, 225]. They can be performed either by changing the weights of the model (e.g., fine-tuning) or by modifying only the model inputs (e.g., prompt engineering, jailbreaking, retrieval-augmented generation). Reconfiguration can be intentional (with the help of adversarial inputs) or unintentional (from unanticipated inputs to the model)."
From Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Domain
- 4. Malicious actors
- Subdomain
- 4.0
- Causal entity
- Human
- Intent
- Other
- Timing
- Post-deployment