Explore 5 source-supported AI security cases for AML.T0005.001 · Train Proxy via Replication in MITRE ATLAS, with evidence, scope, and defensive analysis.
Risk category
Adversaries may replicate a private model. By repeatedly querying the victim's [AI Model Inference API Access](/techniques/AML.T0040), the adversary can collect the target model's inferences into a dataset. The inferences are used as labels for training a separate model offline that will mimic the behavior and performance of the target model. A replicated model that closely mimics the target model is a valuable resource in staging the attack. The adversary can use the replicated model to [Craft Adversarial Data](/techniques/AML.T0043) for various purposes (e.g. [Evade AI Model](/techniques/AML.T0015), [Spamming AI System with Chaff Data](/techniques/AML.T0046)).
NSA, CISA and FBI attributed coordinated distillation campaigns to six China-based AI companies. Their September 2026 advisory describes fraudulent accounts, bulk subscriptions, gray-market proxies, cross-provider routing, request-metadata removal and hidden-reasoning prompts, followed by response collection and quality checks. Distillation trains a model from another model’s outputs; the advisory’s attribution and capability-assessment claims are attributed to the agencies, not presented as independently reproduced measurements or model-weight theft.
ATLAS annotations follow the source SecureFlow steps; they are not a MITRE endorsement of cross-framework mappings.
Google reported campaigns that used compromised credentials, fraudulent accounts and proxies to collect model outputs for distillation: training another model from a provider’s responses. A February 2026 reasoning-focused campaign exceeded 100,000 prompts; later campaigns included some above 100 million. Those are campaign query volumes, not model weights stolen or a measured replication success rate. Google says it disrupted accounts and reduced the usefulness of collected outputs.
ATLAS annotations follow the source SecureFlow steps; they are not a MITRE endorsement of cross-framework mappings.
Anthropic attributed more than 16 million exchanges through roughly 24,000 fraudulent accounts to DeepSeek, Moonshot AI and MiniMax. The flow distinguishes proxy access, authenticated accounts, distributed routing, inference-response collection and downstream model training. Provider-side hunting and verified limits act before outputs leave; potential harms from models lacking safeguards remain Anthropic’s risk assessment, not observed downstream victim counts.
ATLAS annotations follow the source SecureFlow steps; they are not a MITRE endorsement of cross-framework mappings.
Proof Pudding (CVE-2019-20634) is a code repository that describes how ML researchers evaded ProofPoint's email protection system by first building a copy-cat email protection ML model, and using the insights to bypass the live system. More specifically, the insights allowed researchers to craft malicious emails that received preferable scores, going undetected by the system. Each word in an email is scored numerically based on multiple variables and if the overall score of the email is too low, ProofPoint will output an error, labeling it as SPAM.
ATLAS annotations follow the source SecureFlow steps; they are not a MITRE endorsement of cross-framework mappings.
Machine translation services (such as Google Translate, Bing Translator, and Systran Translate) provide public-facing UIs and APIs. A research group at UC Berkeley utilized these public endpoints to create a replicated model with near-production state-of-the-art translation quality. Beyond demonstrating that IP can be functionally stolen from a black-box system, they used the replicated model to successfully transfer adversarial examples to the real production services. These adversarial inputs successfully cause targeted word flips, vulgar outputs, and dropped sentences on Google Translate and Systran Translate websites.
ATLAS annotations follow the source SecureFlow steps; they are not a MITRE endorsement of cross-framework mappings.