Technical vulnerabilities (Robustness - unexpected behaviour)

Regulating under Uncertainty: Governance Options for Generative AI

G'sell (2024)

Source DOI

Sub-category

Risk Domain

7AI System Safety, Failures & Limitations

7.3Lack of capability or robustness

AI systems that fail to perform reliably or effectively under varying conditions, exposing them to errors and failures that can have significant consequences, especially in critical applications or areas that require moral reasoning.

"There is no assurance that generative AI models will consistently behave as their developers and users intend. Unwanted content is not necessarily due to intentional adversarial behavior. Generative AI models can unexpectedly produce potentially harmful content, including materials that are racist, discriminatory, or sexually explicit, or that promote violence, terrorism, or hate."(p. 61)

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Supporting Evidence (1)

"For instance, in February 2024, ChatGPT experienced a notable incident in which the model began generating nonsensical responses. For example, a simple question like, “What is a computer?” led ChatGPT to switch to Spanglish or generate incoherent phrases in the responses.227"

Part of Technical and operational risks