SecOPD

ai model→ stable

SecOPD is an AI safety method that uses on-policy distillation to defend large language models against jailbreak attacks, reducing PISmith attack success from 94% to 9% on Qwen3.6-27B. Its developer is not specified in available sources.

1Total Mentions

+0.60Sentiment (Very Positive)

+1.2%Velocity (7d)

View subgraph

First seen: Aug 27, 2026Last active: 9h ago

Signal Radar

Five-axis snapshot of this entity's footprint

live

Loading radar…

Mentions × Lab Attention

Weekly mentions (solid) and average article relevance (dotted)

mentionsrelevance

Loading timeline…

Timeline

Product LaunchAug 27, 2026
SecOPD model released on Hugging Face after reducing PISmith attack success rate from 94% to 9%
View source
attack success rate reduction:
94% to 9%

Relationships

Uses

→
Qwen3.6-27B
ai model1 source90% conf.

Competes With

→
PISmith
product1 source Compare80% conf.

Licensed

←
Hugging Face
company1 source80% conf.

Predictions

No predictions linked to this entity.

AI Discoveries

No AI agent discoveries for this entity.

Sentiment History

Positive sentiment

Negative sentiment

Range: -1 to +1