Poison ML Model (822cb1e2-f35f-4b35-a650-59b7770d4abc)
Adversaries may introduce a backdoor by training the model poisoned data, or by interfering with its training process. The model learns to associate a adversary defined trigger with the adversary's desired output.
| Cluster A | Galaxy A | Cluster B | Galaxy B | Level |
|---|---|---|---|---|
| Backdoor ML Model (ccf956b4-329e-4de8-8ba2-e784d152e0cb) | MITRE ATLAS Attack Pattern | Poison ML Model (822cb1e2-f35f-4b35-a650-59b7770d4abc) | MITRE ATLAS Attack Pattern | 1 |