AML.T0005.000 · Train Proxy via Gathered AI Artifacts

Explore 1 source-supported AI security cases for AML.T0005.000 · Train Proxy via Gathered AI Artifacts in MITRE ATLAS, with evidence, scope, and defensive analysis.

Risk category

Proxy models may be trained from AI artifacts (such as data, model architectures, and pre-trained models) that are representative of the target model gathered by the adversary. This can be used to develop attacks that require higher levels of access than the adversary has available or as a means to validate pre-existing attacks without interacting with the target model.

Official framework source ↗ · Open interactive explorer ↗

Exercise ·

GPT-2 Model Replication

OpenAI built GPT-2, a language model capable of generating high quality text samples. Over concerns that GPT-2 could be used for malicious purposes such as impersonating others, or generating misleading news articles, fake social media content, or spam, OpenAI adopted a tiered release schedule. They initially released a smaller, less powerful version of GPT-2 along with a technical description of the approach, but held back the full trained model. Before the full model was released by OpenAI, researchers at Brown University successfully replicated the model using information released by OpenAI and open source ML artifacts. This demonstrates that a bad actor with sufficient technical skill and compute resources could have replicated GPT-2 and used it for harmful goals before the AI Security community is prepared.

ATLAS annotations follow the source SecureFlow steps; they are not a MITRE endorsement of cross-framework mappings.

SecureFlow · Read the full case ↗