Findings
AI Total Tokens Elevated
Updated: June 19, 2025
Description
The total number of input and output tokens processed has increased significantly.
This could result in higher costs, increased latency, and potential throttling of requests.
Potential Causes:
- Large inputs or inefficient prompts leading to excessive token consumption.
- Model generating overly detailed responses.
- Misuse of AI service leading to cost spikes.
Remediation
Monitor usage patterns, make adjustments to model configurations accordingly to ensure optimal performance.
Security Frameworks
Unbounded Consumption occurs when a Large Language Model (LLM) application allows users to conduct excessive and uncontrolled inferences, leading to risks such as denial of service (DoS), economic losses, model theft, and service degradation.
Adversaries may target machine learning systems with a flood of requests for the purpose of degrading or shutting down the service. Since many machine learning systems require significant amounts of specialized compute, they are often expensive bottlenecks that can become overloaded. Adversaries can intentionally craft inputs that require heavy amounts of useless compute from the machine learning system.
Adversaries may target different machine learning services to send useless queries or computationally expensive inputs to increase the cost of running services at the victim organization. Sponge examples are a particular type of adversarial data designed to maximize energy consumption and thus operating cost.