Modify AI Model Architecture
Adversaries may directly modify an AI model's architecture to re define it's behavior. This can include adding or removing layers as well as adding pre or post processing operations. The effects could include removing the ability to predict certain classes, adding erroneous operations to increase computation costs, or
- Framework
- MITRE ATLAS
- Maturity
- Demonstrated
- Platforms
- Predictive AI, Generative AI, Agentic AI
- Release
- 2026.05
Overview
Adversaries may directly modify an AI model's architecture to re-define it's behavior. This can include adding or removing layers as well as adding pre or post-processing operations.
The effects could include removing the ability to predict certain classes, adding erroneous operations to increase computation costs, or degrading performance. Additionally, a separate adversary-defined network could be injected into the computation graph, which can change the behavior based on the inputs, effectively creating a backdoor.