Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…
gentic.news
Subgraph Atlas · centered on entity

SecOPD

ai model1 mentions· velocity: 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.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.

0 nodes · 0 edges · loading…
companypersonai_modelproductresearch_labbenchmarkframework
drag to move · scroll to zoom · click a node

Top connections

Hugging Facecompany
103 mentions
→ Center atlas here
Qwen3.6-27Bai model
4 mentions
→ Center atlas here
PISmithproduct
1 mentions
→ Center atlas here
How to read this: the white-ringed node is SecOPD. Surrounding nodes are direct relationships; the second ring is what those neighbors connect to. Edge thickness scales with source-article evidence. Click any node and choose Center graph here to walk the graph.