Back to CWE Database

CWE-1434

Insecure Setting of Generative AI/ML Model Inference Parameters

Weakness Description

The product has a component that relies on a generative AI/ML model configured with inference parameters that produce an unacceptably high rate of erroneous or unexpected outputs.

Generative AI/ML models, such as those used for text generation, image synthesis, and other creative tasks, rely on inference parameters that control model behavior, such as temperature, Top P, and Top K. These parameters affect the model's internal decision-making processes, learning rate, and probability distributions. Incorrect settings can lead to unusual behavior such as text "hallucinations," unrealistic images, or failure to converge during training. The impact of such misconfigurations can compromise the integrity of the application. If the results are used in security-critical operations or decisions, then this could violate the intended security policy, i.e., introduce a vulnerability.

Potential Mitigations

ImplementationSystem ConfigurationOperation

Develop and adhere to robust parameter tuning processes that include extensive testing and validation.

ImplementationSystem ConfigurationOperation

Implement feedback mechanisms to continuously assess and adjust model performance.

Documentation

Provide comprehensive documentation and guidelines for parameter settings to ensure consistent and accurate model behavior.

Common Consequences

IntegrityOther
Varies by ContextUnexpected State

The product can generate inaccurate, misleading, or nonsensical information.

Other
Alter Execution LogicUnexpected StateVaries by Context

If outputs are used in critical decision-making processes, errors could be propagated to other systems or components.

Detection Methods

Automated Dynamic Analysis

Manipulate inference parameters and perform comparative evaluation to assess the impact of selected values. Build a suite of systems using targeted tools that detect problems such as prompt injection (CWE-1427) and other problems. Consider statistically measuring token distribution to see if it is consistent with expected results.

Effectiveness: Moderate

Manual Dynamic Analysis

Manipulate inference parameters and perform comparative evaluation to assess the impact of selected values. Build a suite of systems using targeted tools that detect problems such as prompt injection (CWE-1427) and other problems. Consider statistically measuring token distribution to see if it is consistent with expected results.

Effectiveness: Moderate

Related Weaknesses