Merge 12138823e058bbf7feecc9c31e57b9b82aa4ddac into 406e4a403895cd845a274a15ebf03bd50802d1b3

This commit is contained in:
Brian Mirlenbrink 2023-04-27 16:51:44 +00:00 committed by GitHub
commit 2e0dcbf470
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -179,7 +179,7 @@ Machine translation services (such as Google Translate, Bing Translator, and Sys
## GPT-2 Model Replication
**Summary of Incident:** : OpenAI built GPT-2, a powerful natural language model and adopted a staged-release process to incrementally release 1.5 Billion parameter model. Before the 1.5B parameter model could be released by OpenAI eventually, two ML researchers replicated the model and released it to the public. *Note this is an example of model replication NOT model model extraction. Here, the attacker is able to recover a functionally equivalent model but generally with lower fidelity than the original model, perhaps to do reconnaissance (See ProofPoint attack). In Model extraction, the fidelity of the model is comparable to the original, victim model.*
**Summary of Incident:** : OpenAI built GPT-2, a powerful natural language model and adopted a staged-release process to incrementally release 1.5 Billion parameter model. Before the 1.5B parameter model could be released by OpenAI eventually, two ML researchers replicated the model and released it to the public. *Note this is an example of model replication NOT model extraction. Here, the attacker is able to recover a functionally equivalent model but generally with lower fidelity than the original model, perhaps to do reconnaissance (See ProofPoint attack). In model extraction, the fidelity of the model is comparable to the original, victim model.*
**Mapping to Adversarial Threat Matrix :**
- Using public documentation about GPT-2, ML researchers gathered similar datasets used during the original GPT-2 training.