Poison ML Model (e0eb2b64-aebd-4412-80f3-b71d7805a65f)
Adversaries may introduce a backdoor by training the model poisoned data, or by interfering with its training process. The model learns to associate an adversary-defined trigger with the adversary's desired output.
| Cluster A | Galaxy A | Cluster B | Galaxy B | Level |
|---|---|---|---|---|
| Poison ML Model (e0eb2b64-aebd-4412-80f3-b71d7805a65f) | MITRE ATLAS Attack Pattern | Backdoor ML Model (c704a49c-abf0-4258-9919-a862b1865469) | MITRE ATLAS Attack Pattern | 1 |