Invert ML Model (569d6edd-0140-4ab2-97b1-3635d62f40cc)
Machine learning models' training data could be reconstructed by exploiting the confidence scores that are available via an inference API. By querying the inference API strategically, adversaries can back out potentially private information embedded within the training data. This could lead to privacy violations if the attacker can reconstruct the data of sensitive features used in the algorithm.
| Cluster A | Galaxy A | Cluster B | Galaxy B | Level |
|---|---|---|---|---|
| Invert ML Model (569d6edd-0140-4ab2-97b1-3635d62f40cc) | MITRE ATLAS Attack Pattern | Exfiltration via ML Inference API (3b829988-8bdb-4c4e-a4dd-500a3d3fd3e4) | MITRE ATLAS Attack Pattern | 1 |