Termsslug: classifiers

Classifiers

分类器防护

Detection model components that identify and block policy-violating requests or outputs.

Curated Intelligence

1 items · Page 1/1
OpenAI 官方博客T1·Models
78 pts
OpenAI Details Defenses Against Adversarial Model Distillation

OpenAI outlines a defense framework against adversarial distillation that combines adversarial testing, model training, classifiers, and API-level protections to stop attackers from training unsafeguarded clones on frontier model outputs. It also details hardened protections for protected reasoning and notes that full reasoning transcripts outperform summaries for distillation on SWE-bench Verified and frontier cybersecurity tasks, offering lessons for industry-wide safeguards.