Models
Sub-technique of AML.T0115 Publish Poisoned AI Artifacts
Description
Adversaries may publish poisoned AI models through model registries, code repositories, or other model distribution channels. The model may be newly created or a modified variant of a legitimate model and may contain manipulated weights, configurations, architecture, serialized code, or other components that produce malicious behavior or execute malicious code.
Victims may subsequently download and integrate the model through AI Supply Chain Compromise.
- ATLAS ID
- AML.T0115.001
- Maturity
- RealizedUsed by real adversaries against AI systems in the wild.
- Platforms
- Predictive AIGenerative AIAgentic AI
Mitigations
- AML.M0008Validate AI Model
Model repositories evaluate submissions for backdoors, data leakage, adversarial influence, and unexpected behavior before listing.
- AML.M0016Vulnerability Scanning
Model registries scan uploaded models for unsafe serialization, embedded code, malware, and known vulnerabilities before listing.