ML Attack Staging

Type: tactic

Description: The adversary is leveraging their knowledge of and access to the target system to tailor the attack.

Version: 0.1.0

Created At: 2025-03-04 10:27:40 -0500

Last Modified At: 2025-03-04 10:27:40 -0500

Tactic Order: 13

External References

  • <-- Verify Attack (technique): Testing and validating the effectiveness of a machine learning attack before deployment.
  • <-- Create Proxy ML Model (technique): Building a proxy machine learning model to simulate a victim's model for further analysis or attack preparation.
  • <-- Backdoor ML Model (technique): Embedding backdoors in machine learning models to prepare for future exploitation or malicious activities.
  • <-- Craft Adversarial Data (technique): Creating adversarial data designed to mislead, manipulate, or disrupt machine learning models.