Unbounded Consumption
Unbounded consumption is like leaving a water tap running at full blast indefinitely; it wastes resources, costs a fortune, and can eventually drain the entire system so that no one else can use it.
A vulnerability where an LLM application lacks sufficient rate limiting or token constraints, allowing users to trigger expensive, recursive, or excessively long inference tasks that lead to service outages, budget exhaustion, or unauthorized data exfiltration.
A security failure mode characterized by the absence of deterministic bounds on inference parameters—such as max_tokens, recursion depth, or concurrency limits—enabling adversarial exploitation of the model's compute budget to induce denial-of-service, financial exhaustion, or side-channel model extraction.
evolution
- 2022-11 · historyChatGPT Public Launch
The release of ChatGPT exposed LLMs to massive public query volumes, highlighting the vulnerability of API-based services to resource exhaustion.
- 2023-05 · historyOWASP Top 10 for LLMs
The OWASP project formally identified 'Insecure Output Handling' and 'Denial of Service' as critical risks, codifying the threat of unbounded resource consumption.
- 2023-10 · historyPrompt Injection and Recursion Research
Security researchers demonstrated how recursive prompt chaining could force models into infinite loops, leading to massive compute cost spikes.
- 2024-02 · historyAdoption of Rate Limiting and Token Budgets
Major AI providers and enterprise gateways standardized strict token-per-request limits and cost-capping mechanisms to mitigate unbounded consumption.