diff --git a/pages/case-studies-page.md b/pages/case-studies-page.md index e242497..323912b 100644 --- a/pages/case-studies-page.md +++ b/pages/case-studies-page.md @@ -27,8 +27,8 @@ We welcome any comments, feedback, or new case-studies! Before submitting a case - In this scenario, a security researcher gained initial access to via a "Valid Account" that was created through a misconfiguration. No Adversarial ML techniques were used. - these kinds of attacks illustrate that any attempt to secure ML system should be on top of "traditional" good cybersecurity hygiene such as locking down the system with least privileges, multi factor authentication and monitoring and auditing. -![ClearviewAI](./images/ClearviewAI.png =200x300) -drawing +```![ClearviewAI](./images/ClearviewAI.png =200x300)``` +ClearviewAI ### GPT-2 Model Replication **Summary of Incident:** : OpenAI built GPT-2, a powerful natural language model and calling it "too dangerous to release" adopted a staged-release process to incrementally release 1.5 Billion parameter model. Before the 1.5B parameter model could be released by OpenAI, two ML researchers replicated the model and released it to the public. *Note this is a model replication attack: Here, attacker is able to recover functionally equivalent model (but generally with lower fidelity), perhaps to do reconnaissance (See proof point attack). In Model stealing, the fidelity of the model is comparable to the original, victim model.*