Basic Concept: A denial-of-wallet (DoW) attack deliberately generates excessive API calls or token consumption to exhaust an organization ' s AI budget. Since LLM providers charge based on tokens processed, attackers can cause significant financial damage by driving massive usage. CompTIA SecAI+ Study Guide addresses financial abuse vectors in AI systems.
Why E is Correct: API rate controls limit the number of requests a user or application can make within a defined time period. By capping request frequency, rate controls directly prevent attackers from generating the massive API call volume needed to execute a denial-of-wallet attack.
Why F is Correct: Output token controls cap the maximum number of tokens the model can generate per response. Since billing is based on tokens consumed including outputs, limiting output tokens directly caps the cost per request, preventing attackers from triggering extremely long, expensive responses.
Why A is Wrong: Endpoint access controls manage device or network access. They do not directly limit token consumption or API call volume that drives denial-of-wallet costs.
Why B is Wrong: A CDN distributes content geographically to improve performance and absorb traffic. It does not control LLM API billing or token consumption.
Why C is Wrong: Model fine-tuning adjusts model parameters for improved performance on specific tasks. It is a training process that does not address active cost-exhaustion attacks.
Why D is Wrong: Modality controls restrict which input types such as text, images, or audio a model accepts. While useful for reducing attack surface, they do not directly address the rate or volume of API calls in a DoW attack.
