AML.T0020: Poison Training Data
Adversaries may attempt to poison datasets used by an AI model by modifying the underlying data or its labels. This allows the adversary to embed vulnerabilities in AI models trained on the data that may not be easily detectable. Data poisoning attacks may or may not require modifying the labels. The embedded vulnerability is activated at a later time by data samples with an Insert Backdoor Trigger
Poisoned data can be introduced via AI Supply Chain Compromise or the data may be poisoned after the adversary gains Initial Access to the system.
Standards mapping
Where this fits in a TurboPentest engagement
This weakness is not covered by the automated black-box pentest. IntegSec pentesters cover it in a manual engagement.
Frequently asked questions
What is AML.T0020 Poison Training Data?
Adversaries may attempt to poison datasets used by an AI model by modifying the underlying data or its labels. This allows the adversary to embed vulnerabilities in AI models trained on the data that may not be easily detectable. Data poisoning attacks may or may not require modifying the labels. The embedded vulnerability is activated at a later time by data samples with an Insert Backdoor Trigger Poisoned data can be introduced via AI Supply Chain Compromise or the data may be poisoned after the adversary gains Initial Access to the system.
Which tactics does AML.T0020 belong to?
AML.T0020 maps to the Resource Development, Persistence tactics.
Does TurboPentest test for Poison Training Data?
This weakness is not covered by the automated black-box pentest. IntegSec pentesters cover it in a manual engagement.
Related MITRE ATLAS techniques
- Resource DevelopmentAML.T0002: Acquire Public AI Artifacts
- Resource DevelopmentAML.T0008: Acquire Infrastructure
- Resource DevelopmentAML.T0016: Obtain Capabilities
- Resource DevelopmentAML.T0017: Develop Capabilities
- Resource DevelopmentAML.T0019: Publish Poisoned Datasets
- Resource DevelopmentAML.T0021: Establish Accounts
About this reference
These security references are maintained by IntegSec, an offensive-security firm whose team holds CISSP, OSCP, and OSCE certifications and has run thousands of penetration tests. Content is kept current as tools, standards, and attack techniques evolve.
Find these issues before an attacker does
TurboPentest runs an agentic AI pentest against your target and reports findings with proof, from $99 per target.
Start a pentest