Robustness
AI Risk"This is the risk of the system failing or being unable to recover upon encountering invalid, noisy, or out-of-distribution (OOD) inputs."
Overview
A source-backed snapshot of this AI risk.
Risk profile
How the MIT AI Risk Repository categorizes this risk.
Merged risk records
Source records unified into this canonical risk concept.
MITRISK-Tan2022-15.01.05 - Robustness
"This is the risk of the system failing or being unable to recover upon encountering invalid, noisy, or out-of-distribution (OOD) inputs."
MITRISK-InfoComm2023-43.01.05 - Robustness
"These evaluations assess the quality, stability, and reliability of a LLM's performance when faced with unexpected, out-of-distribution or adversarial inputs. Robustness evaluation is essential in ensuring that a LLM is suitable for real-world applications by assessing its resilience to various perturbations."
Mitigations
Defenses that may help with related attacks.
Source evidence
Research source for this risk, when available.
Included resource
The Risks of Machine Learning Systems
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.