Text Classification
Laya
ONNX
Safetensors
English
German
prompt-injection
data-exfiltration
llm-security
agent-security
system-one
multilingual
Instructions to use TextCortex/laya-cybersec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use TextCortex/laya-cybersec with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download benchmark_results.json from TextCortex/laya-cybersec: direct link, hf CLI and curl.
- Browser
- Download file 4.93 kB
-
https://huggingface.co/TextCortex/laya-cybersec/resolve/main/benchmark_results.json
- Command line
-
hf download hf://TextCortex/laya-cybersec/benchmark_results.json
-
curl -L -o benchmark_results.json https://huggingface.co/TextCortex/laya-cybersec/resolve/main/benchmark_results.json
4.93 kB
| { | |
| "type": "aggregate_r2a_regression_comparison", | |
| "checkpoint": "R2a", | |
| "models": [ | |
| { | |
| "model": "laya-cybersec-r2a", | |
| "name": "Laya R2a", | |
| "full_en": { | |
| "n": 510, | |
| "attacks": 256, | |
| "clean": 254, | |
| "auroc": 0.9155004306102362, | |
| "caught": 140, | |
| "false_alarms": 2, | |
| "recall": 0.546875, | |
| "fpr": 0.007874015748031496 | |
| }, | |
| "full_de": { | |
| "n": 510, | |
| "attacks": 256, | |
| "clean": 254, | |
| "auroc": 0.8780065821850394, | |
| "caught": 151, | |
| "false_alarms": 9, | |
| "recall": 0.58984375, | |
| "fpr": 0.03543307086614173 | |
| }, | |
| "skills_en": { | |
| "n": 48, | |
| "attacks": 27, | |
| "clean": 21, | |
| "auroc": 0.927689594356261, | |
| "caught": 18, | |
| "false_alarms": 0 | |
| }, | |
| "skills_de": { | |
| "n": 48, | |
| "attacks": 27, | |
| "clean": 21, | |
| "auroc": 0.9329805996472663, | |
| "caught": 18, | |
| "false_alarms": 0 | |
| }, | |
| "pdf": { | |
| "n": 730, | |
| "attacks": 107, | |
| "clean": 623, | |
| "auroc": 0.8855927753859077, | |
| "caught": 81, | |
| "false_alarms": 0 | |
| }, | |
| "decision_rule": "score > 0.95" | |
| }, | |
| { | |
| "model": "jev", | |
| "name": "Jev", | |
| "full_en": { | |
| "auroc": 0.9799920029527559, | |
| "n": 510 | |
| }, | |
| "full_de": { | |
| "auroc": 0.9564391609251969, | |
| "n": 510 | |
| }, | |
| "skills_en": { | |
| "n": 48, | |
| "attacks": 27, | |
| "clean": 21, | |
| "auroc": 0.9841269841269841, | |
| "caught": 25, | |
| "false_alarms": 1 | |
| }, | |
| "skills_de": { | |
| "n": 48, | |
| "attacks": 27, | |
| "clean": 21, | |
| "auroc": 0.9603174603174603, | |
| "caught": 25, | |
| "false_alarms": 2 | |
| }, | |
| "pdf": { | |
| "n": 730, | |
| "attacks": 107, | |
| "clean": 623, | |
| "auroc": 0.978525674682348, | |
| "caught": 73, | |
| "false_alarms": 2 | |
| }, | |
| "decision_rule": "score > 0.5" | |
| }, | |
| { | |
| "model": "TextCortex/clef-cybersecurity", | |
| "name": "clef-cybersecurity", | |
| "full_en": { | |
| "n": 510, | |
| "attacks": 256, | |
| "clean": 254, | |
| "auroc": 0.9925335260826772, | |
| "caught": 232, | |
| "false_alarms": 0 | |
| }, | |
| "full_de": { | |
| "n": 510, | |
| "attacks": 256, | |
| "clean": 254, | |
| "auroc": 0.9743940698818898, | |
| "caught": 241, | |
| "false_alarms": 17 | |
| }, | |
| "skills_en": { | |
| "n": 48, | |
| "attacks": 27, | |
| "clean": 21, | |
| "auroc": 1.0, | |
| "caught": 23, | |
| "false_alarms": 0 | |
| }, | |
| "skills_de": { | |
| "n": 48, | |
| "attacks": 27, | |
| "clean": 21, | |
| "auroc": 0.9171075837742504, | |
| "caught": 26, | |
| "false_alarms": 3 | |
| }, | |
| "pdf": { | |
| "n": 730, | |
| "attacks": 107, | |
| "clean": 623, | |
| "auroc": 0.9856212778086137, | |
| "caught": 84, | |
| "false_alarms": 3 | |
| }, | |
| "decision_rule": "score > 0.5" | |
| }, | |
| { | |
| "model": "Cloudflare/clef-flash", | |
| "name": "CLEF Flash (base)", | |
| "full_en": { | |
| "n": 510, | |
| "attacks": 256, | |
| "clean": 254, | |
| "auroc": 0.9587613804133859, | |
| "caught": 136, | |
| "false_alarms": 0 | |
| }, | |
| "full_de": { | |
| "n": 510, | |
| "attacks": 256, | |
| "clean": 254, | |
| "auroc": 0.9391455462598425, | |
| "caught": 130, | |
| "false_alarms": 0 | |
| }, | |
| "skills_en": { | |
| "n": 48, | |
| "attacks": 27, | |
| "clean": 21, | |
| "auroc": 0.9761904761904762, | |
| "caught": 14, | |
| "false_alarms": 0 | |
| }, | |
| "skills_de": { | |
| "n": 48, | |
| "attacks": 27, | |
| "clean": 21, | |
| "auroc": 0.9047619047619048, | |
| "caught": 12, | |
| "false_alarms": 0 | |
| }, | |
| "pdf": { | |
| "n": 730, | |
| "attacks": 107, | |
| "clean": 623, | |
| "auroc": 0.8144492281843957, | |
| "caught": 6, | |
| "false_alarms": 0 | |
| }, | |
| "decision_rule": "score > 0.5" | |
| } | |
| ], | |
| "cohort": { | |
| "full_per_language": 510, | |
| "skills_per_language": 48, | |
| "pdf_attacks": 107, | |
| "clean_pdfs": 623 | |
| }, | |
| "scope": "Previously inspected internal regression sets; not a public leaderboard or fresh blind test.", | |
| "threshold_note": "Strict >0.5 for both CLEF models and Jev; strict >0.95 for Laya R2a. Recall and false alarms are not equal-threshold comparisons.", | |
| "backend_note": "R2a full-suite results use the saved batched GPU run; matched skill/PDF references use saved local scores. Backend precision causes small score differences; GPU English-skills AUROC was 0.9268077601410935.", | |
| "base_clef_evaluation": { | |
| "type": "unchanged_local_base", | |
| "model": "Cloudflare/clef-flash", | |
| "revision": "17f0b0ad64efb65d273590632833508766b2aae6", | |
| "scope": "Unchanged native checkpoint, evaluated locally on the matched cohorts with token-bounded windows. Not the Cloudflare hosted API run." | |
| } | |
| } | |