Common Weakness Enumeration

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.

See More

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.

This listing shows possible areas for which the given weakness could appear. These may be for specific named Languages, Operating Systems, Architectures, Paradigms, Technologies, or a class of such platforms. The platform is listed along with how frequently the given weakness appears for that instance.

Languages	Class: Not Language-Specific (Undetermined Prevalence)
Architectures	Class: Not Architecture-Specific (Undetermined Prevalence)
Technologies	AI/ML (Undetermined Prevalence) Class: Not Technology-Specific (Undetermined Prevalence)

Example 1

Assume the product offers an LLM-based AI coding assistant to help users to write code as part of an Integrated Development Environment (IDE). Assume the model has been trained on real-world code, and the model behaves normally under its default settings. Suppose there is a default temperature of 1, with a range of temperature values from 0 (most deterministic) to 2.

Consider the following configuration.

The problem is that the configuration contains a temperature hyperparameter that is higher than the default. This significantly increases the likelihood that the LLM will suggest a package that did not exist at training time, a behavior sometimes referred to as "package hallucination." Note that other possible behaviors could arise from higher temperature, not just package hallucination.

An adversary could anticipate which package names could be generated and create a malicious package. For example, it has been observed that the same LLM might hallucinate the same package regularly. Any code that is generated by the LLM, when run by the user, would download and execute the malicious package. This is similar to typosquatting.

The risk could be reduced by lowering the temperature so that it reduces the unpredictable outputs and has a better chance of staying more in line with the training data. If the temperature is set too low, then some of the power of the model will be lost, and it may be less capable of producing solutions for rarely-encountered problems that are not reflected in the training data. However, if the temperature is not set low enough, the risk of hallucinating package names may still be too high. Unfortunately, the "best" temperature cannot be determined a priori, and sufficient empirical testing is needed.

In addition to more restrictive temperature settings, consider adding guardrails that test that independently verify any referenced package to ensure that it exists, is not obsolete, and comes from a trusted party.

Note that reducing temperature does not entirely eliminate the risk of package hallucination. Even with very low temperatures or other settings, there is still a small chance that a non-existent package name will be generated.

This MemberOf Relationships table shows additional CWE Categories and Views that reference this weakness as a member. This information is often useful in understanding where a weakness fits within the context of external information sources.