Model threat profile
Qwen
How agents fingerprinted to the Qwen family behave against our bait. Fingerprinting infers the most likely model family from behaviour; it is probabilistic, not attribution of a specific vendor deployment.
Detections
39
Confirmed
9
Avg. confidence
78%
Bait types
5
Most effective bait against Qwen
On-chain bait13 · 33%
Web lure8 · 21%
Decoy MCP7 · 18%
Honey skill7 · 18%
Decoy doc4 · 10%
Recent detections
| ID | Severity | Bait | Region | Conf. |
|---|---|---|---|---|
| NRS-4077 | Suspected | Honey skill | Singapore, SG | 89% |
| NRS-4025 | Suspected | Decoy MCP | Mumbai, IN | 64% |
| NRS-4060 | Watch | Web lure | Hong Kong, HK | 95% |
| NRS-4081 | Confirmed | Web lure | Singapore, SG | 98% |
| NRS-4056 | Confirmed | On-chain bait | Tokyo, JP | 75% |
| NRS-4012 | Suspected | On-chain bait | Tokyo, JP | 59% |
| NRS-4097 | Confirmed | Decoy doc | Oregon, US | 58% |
| NRS-4079 | Suspected | Decoy doc | Singapore, SG | 60% |
| NRS-4055 | Watch | On-chain bait | Tokyo, JP | 82% |
| NRS-4096 | Watch | Decoy MCP | Oregon, US | 79% |
Tailored to you
Track Qwen activity against your stack.
Filter the feed to the models that matter to you, and get alerted when one touches your assets. Enterprise adds bait deployed inside your own environment.