Understand this story
OpenAI shared new research on countering knowledge distillation attacks against its models, outlining safeguards including adversarial training, classifiers, API protections, and investigations into coordinated activity. In adaptive black-box evaluations, the average attack success rate for extracting reasoning from earlier requests fell from 54.0% for GPT‐6 Astra to 0.2% for GPT‐6.2 Astra, while the success rate for extracting reasoning from the current request dropped from 22.9% to 0.9%. OpenAI also said it has identified multiple unauthorized distillation operations this year and takes action against thousands to tens of thousands of accounts each week. There are currently no other evidence-backed developments.
AI-generated from public reports
Latest development · Report
OpenAI Publishes Research on Model Distillation Abuse and DefensesDevelopments
1 confirmed developments
- Source:OpenAI News
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 21
OpenAIFirst-party
OpenAI Publishes Research on Model Distillation Abuse and Defenses
OpenAI shared new research on countering the knowledge distillation of its models, noting that knowledge distillation may reproduce powerful AI capabilities without the accompanying safeguards. The research also explores how capabilities are transferred and how OpenAI detects and blocks coordinated attempts.
Nov 20
OpenAI NewsFirst-partySelected
OpenAI Details Defenses Against Adversarial Knowledge Distillation and the Risks of Reasoning Extraction
OpenAI has unveiled defenses against adversarial knowledge distillation that use adversarial training, classifiers, API protections, and investigations into coordinated activity to limit the extraction of model capabilities and protected reasoning. In adaptive black-box evaluations, the average attack success rate for extracting reasoning from earlier requests fell from 54.0% for GPT‑6 Astra to 0.2% for GPT‑6.2 Astra, while the success rate for extracting reasoning from the current request dropped from 22.9% to 0.9%. OpenAI also reported uncovering multiple unauthorized distillation campaigns this year, with enforcement actions affecting thousands to tens of thousands of accounts each week.
AI Trends