Resource-Intensive Queries
Sub-technique of AML.T0034 Cost Harvesting
Description
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 [[genai]]. For vision and language models, "sponge examples" [[arxiv]] 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.
- ATLAS ID
- AML.T0034.001
- Maturity
- FeasibleShown to be possible in principle (proof of concept).
- Platforms
- Predictive AIGenerative AIAgentic AI
Mitigations
- AML.M0035AI Red Team
Submit controlled requests designed to consume disproportionate inference resources. Verify input constraints, timeouts, workload limits, resource isolation, and cost monitoring.
- AML.M0036Limit AI Workload Resource Consumption
Bound input size, output size, execution time, memory, and compute consumed by resource-intensive queries.
Case studies that use it
No ATLAS case study records this technique yet. Browse all case studies.