Resource-Intensive Queries
Adversaries may craft inputs specifically designed to increase the compute resources required for processing. For generative AI models, adversaries may use long input sequences, requests for extremely long outputs, or prompts that require complex reasoning as strategies for increasing compute costs OWASP Top 10 for LLM
- Framework
- MITRE ATLAS
- Maturity
- Feasible
- Platforms
- Predictive AI, Generative AI, Agentic AI
- Release
- 2026.05
Overview
Adversaries may craft inputs specifically designed to increase the compute resources required for processing.
For generative AI models, adversaries may use long input sequences, requests for extremely long outputs, or prompts that require complex reasoning as strategies for increasing compute costs OWASP Top 10 for LLM Applications 2025. For vision and language models, "sponge examples" [2006.03463] Sponge Examples: Energy-Latency Attacks on Neural Networks can be used to maximize energy consumption and decision latency. Utilizing fewer resource-intensive queries instead of simply flooding the model with excessive queries may be more difficult to detect and block or limit.