scthornton/securecode-web
Viewer • Updated • 1.38k • 2.48k • 11
Scott Thornton PRO
scthornton
AI & ML interests
AI/ML Security
Recent Activity
updated a dataset 1 day ago
scthornton/securecode-web updated a model 18 days ago
scthornton/gemma4-26b-securecode published a model 21 days ago
scthornton/gemma4-26b-securecodeOrganizations
updated a
dataset 1 day ago
updated a
model 18 days ago
published a
model 21 days ago
updated 5
models about 1 month ago
scthornton/chronos-t5-small-poisoned-demo
Time Series Forecasting • 46.2M • Updated • 101
scthornton/bert-tiny-multi-attack-demo
Text Classification • Updated • 7
scthornton/bert-tiny-poisoned-demo
Text Classification • Updated • 4
scthornton/granite-20b-code-securecode
Text Generation • Updated • 6 • 1
scthornton/starcoder2-15b-securecode
Text Generation • Updated • 20
upvoted an article about 1 month ago
Article
IntentGuard: Building a Production-Grade Vertical Intent Classifier for LLM Safety
•
2
reacted to perfecXion's post with 👍 about 2 months ago
Post
2563
# IntentGuard: Open-Source Vertical Intent Classifiers for LLM Guardrails
Three models published to the Hub:
- [perfecXion/intentguard-finance]( perfecXion/intentguard-finance)
- [perfecXion/intentguard-healthcare]( perfecXion/intentguard-healthcare)
- [perfecXion/intentguard-legal]( perfecXion/intentguard-legal)
DeBERTa-v3-xsmall fine-tuned for three-way classification: **allow**, **deny**, or **abstain**. ONNX + INT8 quantized, under 80MB, p99 <30ms on CPU. Margin-based thresholds (not argmax) — uncertain queries route to clarification instead of forcing a guess.
**Eval results (adversarial test sets, ~470-480 examples per vertical):**
| Vertical | Accuracy | Legit-Block Rate | Off-Topic-Pass Rate |
|----------|----------|------------------|---------------------|
| Finance | 99.6% | 0.00% | 0.00% |
| Healthcare | 98.9% | 0.00% | 0.98% |
| Legal | 97.9% | 0.00% | 0.50% |
Apache 2.0. Full pipeline + Docker configs on [GitHub](https://github.com/perfecxion-ai/intentguard).
Feedback welcome on domain coverage, adversarial robustness, and multilingual demand.
Three models published to the Hub:
- [perfecXion/intentguard-finance]( perfecXion/intentguard-finance)
- [perfecXion/intentguard-healthcare]( perfecXion/intentguard-healthcare)
- [perfecXion/intentguard-legal]( perfecXion/intentguard-legal)
DeBERTa-v3-xsmall fine-tuned for three-way classification: **allow**, **deny**, or **abstain**. ONNX + INT8 quantized, under 80MB, p99 <30ms on CPU. Margin-based thresholds (not argmax) — uncertain queries route to clarification instead of forcing a guess.
**Eval results (adversarial test sets, ~470-480 examples per vertical):**
| Vertical | Accuracy | Legit-Block Rate | Off-Topic-Pass Rate |
|----------|----------|------------------|---------------------|
| Finance | 99.6% | 0.00% | 0.00% |
| Healthcare | 98.9% | 0.00% | 0.98% |
| Legal | 97.9% | 0.00% | 0.50% |
docker run -p 8080:8080 ghcr.io/perfecxion/intentguard:finance-latest
curl -X POST http://localhost:8080/v1/classify \
-H "Content-Type: application/json" \
-d '{"messages": [{"role": "user", "content": "What are current mortgage rates?"}]}'Apache 2.0. Full pipeline + Docker configs on [GitHub](https://github.com/perfecxion-ai/intentguard).
Feedback welcome on domain coverage, adversarial robustness, and multilingual demand.
reacted to their post with 👀🚀 about 2 months ago
Post
1925
# SecureCode Dataset Family Update: 2,185 Security Examples, Framework-Specific Patterns, Clean Parquet Loading
Hey y'all,
Quick update on the SecureCode dataset family. We've restructured things and fixed several issues:
**What changed:**
- The datasets are now properly split into three repos: [unified]( scthornton/securecode) (2,185), [web]( scthornton/securecode-web) (1,378), [AI/ML]( scthornton/securecode-aiml) (750)
- All repos now use Parquet format --
- SecureCode Web now includes 219 framework-specific examples (Express, Django, Spring Boot, Flask, Rails, Laravel, ASP.NET Core, FastAPI, NestJS)
- Data cards have been corrected and split sizes fixed
**Why it matters:**
With AI-generated code accounting for 60%+ of some codebases (Checkmarx 2025), security training data is more important than ever. Every example in SecureCode is grounded in a real CVE with 4-turn conversations that mirror actual developer-AI workflows.
If you're working on code generation models, I'd love to hear how you're approaching the security angle. Are there vulnerability categories or frameworks you'd like to see covered?
Paper: [arxiv.org/abs/2512.18542](https://arxiv.org/abs/2512.18542)
Hey y'all,
Quick update on the SecureCode dataset family. We've restructured things and fixed several issues:
**What changed:**
- The datasets are now properly split into three repos: [unified]( scthornton/securecode) (2,185), [web]( scthornton/securecode-web) (1,378), [AI/ML]( scthornton/securecode-aiml) (750)
- All repos now use Parquet format --
load_dataset() just works, no deprecated loading scripts- SecureCode Web now includes 219 framework-specific examples (Express, Django, Spring Boot, Flask, Rails, Laravel, ASP.NET Core, FastAPI, NestJS)
- Data cards have been corrected and split sizes fixed
**Why it matters:**
With AI-generated code accounting for 60%+ of some codebases (Checkmarx 2025), security training data is more important than ever. Every example in SecureCode is grounded in a real CVE with 4-turn conversations that mirror actual developer-AI workflows.
If you're working on code generation models, I'd love to hear how you're approaching the security angle. Are there vulnerability categories or frameworks you'd like to see covered?
Paper: [arxiv.org/abs/2512.18542](https://arxiv.org/abs/2512.18542)
posted an update about 2 months ago
Post
1925
# SecureCode Dataset Family Update: 2,185 Security Examples, Framework-Specific Patterns, Clean Parquet Loading
Hey y'all,
Quick update on the SecureCode dataset family. We've restructured things and fixed several issues:
**What changed:**
- The datasets are now properly split into three repos: [unified]( scthornton/securecode) (2,185), [web]( scthornton/securecode-web) (1,378), [AI/ML]( scthornton/securecode-aiml) (750)
- All repos now use Parquet format --
- SecureCode Web now includes 219 framework-specific examples (Express, Django, Spring Boot, Flask, Rails, Laravel, ASP.NET Core, FastAPI, NestJS)
- Data cards have been corrected and split sizes fixed
**Why it matters:**
With AI-generated code accounting for 60%+ of some codebases (Checkmarx 2025), security training data is more important than ever. Every example in SecureCode is grounded in a real CVE with 4-turn conversations that mirror actual developer-AI workflows.
If you're working on code generation models, I'd love to hear how you're approaching the security angle. Are there vulnerability categories or frameworks you'd like to see covered?
Paper: [arxiv.org/abs/2512.18542](https://arxiv.org/abs/2512.18542)
Hey y'all,
Quick update on the SecureCode dataset family. We've restructured things and fixed several issues:
**What changed:**
- The datasets are now properly split into three repos: [unified]( scthornton/securecode) (2,185), [web]( scthornton/securecode-web) (1,378), [AI/ML]( scthornton/securecode-aiml) (750)
- All repos now use Parquet format --
load_dataset() just works, no deprecated loading scripts- SecureCode Web now includes 219 framework-specific examples (Express, Django, Spring Boot, Flask, Rails, Laravel, ASP.NET Core, FastAPI, NestJS)
- Data cards have been corrected and split sizes fixed
**Why it matters:**
With AI-generated code accounting for 60%+ of some codebases (Checkmarx 2025), security training data is more important than ever. Every example in SecureCode is grounded in a real CVE with 4-turn conversations that mirror actual developer-AI workflows.
If you're working on code generation models, I'd love to hear how you're approaching the security angle. Are there vulnerability categories or frameworks you'd like to see covered?
Paper: [arxiv.org/abs/2512.18542](https://arxiv.org/abs/2512.18542)
upvoted an article about 2 months ago
Article
AI Coding Assistants Keep Shipping Vulnerable Code -- Here's What We're Doing About It
•
3
published an article about 2 months ago
Article
AI Coding Assistants Keep Shipping Vulnerable Code -- Here's What We're Doing About It
•
3
commented on GGML and llama.cpp join HF to ensure the long-term progress of Local AI about 2 months ago
Congratulations to all involved! These are great additions!
upvoted an article about 2 months ago
Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +4
•
504
updated 3
models 2 months ago