CoolFace
Modelpublic

ApiFort/LLMFort-jailbreak_content_injection

sourceHugging Faceupdated 2mo agoView on Hugging Face
0likes7downloads
Model Card

🛡️ LLM-Fort Guardrails Suite (v1)

![Base Model](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) ![Framework](https://github.com/huggingface/peft) ![Collection](https://huggingface.co/collections/ApiFort/llmfort-guardrails-v1)

LLM-Fort Guardrails is a suite of 7 security-focused LoRA adapters fine-tuned on top of Qwen/Qwen3-4B-Instruct-2507. These adapters serve as lightweight, high-performance security guardrails mapped to critical safety boundaries.

By offloading classification and security checks to lightweight adapters, the system achieves enterprise-grade security filtering without degrading the inference performance of the main application model.

📖 Collection Page: ApiFort/llmfort-guardrails-v1

🗺️ Category Mappings

Vulnerability CategoryAdapter Model IDDescription
🚨 [Prompt Injection](https://huggingface.co/ApiFort/jailbreak_content_injection)jailbreak_content_injectionDetects direct/indirect prompt injection and jailbreak attempts
🕵️ [PII Extraction](https://huggingface.co/ApiFort/pii)piiIdentifies and extracts PII (person names, ID numbers, etc.)
💻 [Code Security](https://huggingface.co/ApiFort/code_security)code_securityScans code snippets for software vulnerabilities (SQLi, SSRF, XSS)
🚦 [Excessive Agency](https://huggingface.co/ApiFort/excessive_agency)excessive_agencyIntercepts unauthorized or destructive critical tool calls
🔒 [System Prompt Leakage](https://huggingface.co/ApiFort/system_prompt_leakage)system_prompt_leakageDetects attempts to extract developer system instructions
⚠️ [Content Safety](https://huggingface.co/ApiFort/content_safety)content_safetyBlocks hate speech, harassment, and general unsafe content
🛑 [Unbounded Consumption](https://huggingface.co/ApiFort/unbounded_consumption)unbounded_consumptionMitigates resource exhaustion and compute DoS attacks

📈 Performance & Evaluation

Visual comparison of baseline performance versus the trained adapters:

[image]

Benchmark Results

Below is the exact accuracy performance measured across our evaluation test suites:

CategoryGemma 4-E4B-itQwen 3.5 4BQwen3 4B Instructllmfort ai guardrail v.1.0
[Prompt Injection](https://huggingface.co/ApiFort/jailbreak_content_injection)56.30%64.70%84.14%98.10%
[PII Extraction](https://huggingface.co/ApiFort/pii)84.36%75.84%78.31%95.30%
[Code Security](https://huggingface.co/ApiFort/code_security)83.30%75.10%76.20%90.07%
[Excessive Agency](https://huggingface.co/ApiFort/excessive_agency)60.90%68.80%53.80%96.50%
[System Prompt Leakage](https://huggingface.co/ApiFort/system_prompt_leakage)79.40%79.70%78.70%98.08%
[Content Safety](https://huggingface.co/ApiFort/content_safety)84.00%78.80%76.00%95.30%
[Unbounded Consumption](https://huggingface.co/ApiFort/unbounded_consumption)63.00%63.30%55.00%99.79%

🗃️ Training & Validation Datasets

The adapters were trained and validated on the following dataset references:

CategorySource Datasets / References
[Prompt Injection](https://huggingface.co/ApiFort/jailbreak_content_injection)BIPIA, Deepset, Internal 1K Validation
[PII Extraction](https://huggingface.co/ApiFort/pii)AI4Privacy PII Masking 300k (EN, TR, FR, DE, ES)
[Code Security](https://huggingface.co/ApiFort/code_security)r2vul, securecode_web
[Excessive Agency](https://huggingface.co/ApiFort/excessive_agency)jinjinyien/ToolSafety, minpeter/xlam-function-calling-60k-parsed
[System Prompt Leakage](https://huggingface.co/ApiFort/system_prompt_leakage)S-Labs/prompt-injection-dataset, Synthetic data
[Content Safety](https://huggingface.co/ApiFort/content_safety)NVIDIA Nemotron-3.5-Content-Safety-Dataset, Wildguardmix
[Unbounded Consumption](https://huggingface.co/ApiFort/unbounded_consumption)neuralchemy/prompt-injection-Threat-Matrix, Lakera/mosscappromptinjection