Denial of AI Service
Description
Adversaries may target AI-enabled systems with a flood of requests for the purpose of degrading or shutting down the service.
Since many AI 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 AI system.
- ATLAS ID
- AML.T0029
- Maturity
- DemonstratedShown to work in research or red-team exercises.
- Platforms
- Predictive AIGenerative AIAgentic AI
Mitigations
- AML.M0004Limit AI Service Query Volume and Rate
Limit the number of queries users can perform in a given interval to prevent a denial of service.
- AML.M0015Predictive AI Adversarial Input Detection
Assess queries before inference call or enforce timeout policy for queries which consume excessive resources.
- AML.M0019Control Access to AI Models and Data in Production
Access controls on model APIs can prevent an adversary from excessively querying and disabling the system.
- AML.M0035AI Red Team
Submit adversarial workloads and exercise dependency failures that could exhaust inference or supporting services. Apply quotas, concurrency limits, timeouts, resource isolation, and graceful degradation based on findings.
- AML.M0036Limit AI Workload Resource Consumption
Limit the resources consumed by individual requests to reduce denial of service from computationally expensive inputs.