MITRE ATLAStactic
AML.TA0001 AI Attack Staging
- Created
- 2021-05-13
Description
The adversary is leveraging their knowledge of and access to the target system to tailor the attack.
AI Attack Staging consists of techniques adversaries use to prepare their attack on the target AI model.
Techniques can include training proxy models, poisoning the target model, and crafting adversarial data to feed the target model.
Some of these techniques can be performed in an offline manner and are thus difficult to mitigate.
These techniques are often used to achieve the adversary's end goal.
Related
Referenced by MITRE ATLAS · tactic (17)
- AML.T0102 Generate Malicious Commands technique
- AML.T0088 Generate Deepfakes technique
- AML.T0018.002 Embed Malware sub-technique
- AML.T0005 Create Proxy AI Model technique
- AML.T0005.000 Train Proxy via Gathered AI Artifacts sub-technique
- AML.T0005.001 Train Proxy via Replication sub-technique
- AML.T0005.002 Use Pre-Trained Model sub-technique
- AML.T0018 Manipulate AI Model technique
- AML.T0018.000 Poison AI Model sub-technique
- AML.T0018.001 Modify AI Model Architecture sub-technique
- AML.T0042 Verify Attack technique
- AML.T0043 Craft Adversarial Data technique
- AML.T0043.000 White-Box Optimization sub-technique
- AML.T0043.001 Black-Box Optimization sub-technique
- AML.T0043.002 Black-Box Transfer sub-technique
- AML.T0043.003 Manual Modification sub-technique
- AML.T0043.004 Insert Backdoor Trigger sub-technique