Laya fine-tune that scans untrusted text (extracted files, knowledge-base documents, agent skills, tool descriptions) for prompt injection and data exfiltration in English and German, as a noul question answered in one forward pass. 322M parameters, PyTorch and ONNX.
Superagent's 27B security decision model. It scores 2 to 16 supplied options in one forward pass and returns a probability for each, for triaging prompt injection, agent tool calls, code changes, logs and alerts. Apache-2.0 weights (gated, auto-approved) plus a hosted API.
Decides
noul, classify
choice, score, noul, classify, route
Architecture
laya
security-one
Fine-tuned from
convaiinnovations/laya-multilingual
denis-pplx/autojev-27b
License
Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Superagent
Input price
—
—
Decision accuracy
—
99.8%
Calibration error
—
—
Valid action rate
—
—
Median latency
95.4 ms
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between laya-cybersec and security-one?
laya-cybersec is from TextCortex and security-one from Superagent. laya-cybersec has open weights you can download and run; security-one has open weights and a hosted API. Both answer noul and classify questions. Only security-one answers choice, score and route. security-one reads up to 256K tokens of state, against 1K tokens for laya-cybersec. laya-cybersec is the smaller model, at 322M parameters to 27B. laya-cybersec is licensed other; security-one, apache-2.0.
Which is more accurate, laya-cybersec or security-one?
Only security-one publishes an accuracy figure (99.8% on BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70)); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, laya-cybersec or security-one?
laya-cybersec: Free (open weights). security-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run laya-cybersec or security-one locally?
Yes, both: systemone pull textcortex/laya-cybersec and systemone pull superagent/security-one download the weights.
p95 latency
149 ms
—
Evaluation suite
TextCortex saved run: 279 single-window inputs, PyTorch batch one
