LLM Security

Generative AI is quickly changing the cybersecurity landscape. CoreValue provides built-in security measures powered by Meta's state-of-the-art security models to protect your LLM applications.

Security Implementation

CoreValue's LLM security is powered by two advanced models from Meta:

1. Prompt Guard (86M): A specialized model for detecting:

   • Direct prompt injections
   • Indirect/embedded malicious instructions
   • Jailbreak attempts
   • Multi-language attacks (supports 8 languages)

2. Advanced Security Analysis: Optional deeper security analysis using Meta's Llama Guard (3.8B) for comprehensive threat detection across 14 categories:

   Category	Description
   Violent Crimes	Violence toward people or animals
   Non-Violent Crimes	Financial crimes, property crimes, cyber crimes
   Sex-Related Crimes	Trafficking, assault, harassment
   Child Exploitation	Any content related to child abuse
   Defamation	False statements harming reputation
   Specialized Advice	Unauthorized financial/medical/legal advice
   Privacy	Handling of sensitive personal information
   Intellectual Property	Copyright and IP violations
   Indiscriminate Weapons	Creation of dangerous weapons
   Hate Speech	Content targeting protected characteristics
   Suicide & Self-Harm	Content promoting self-injury
   Sexual Content	Adult content and erotica
   Elections	Misinformation about voting
   Code Interpreter Abuse	Malicious code execution attempts

Quick Start

To enable LLM security in CoreValue, simply add Cova-LLM-Security-Enabled: true to your request headers. For advanced security analysis using Llama Guard, add Cova-LLM-Security-Advanced: true:

curl https://gateway.corevalue.dev/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COVA_API_KEY" \
  -H "Cova-LLM-Security-Enabled: true" \
  -H "Cova-LLM-Security-Advanced: true" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "How do I enable LLM security with corevalue?"
      }
    ]
}'

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://gateway.corevalue.dev/v1",
    api_key=os.getenv("COVA_API_KEY"),
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "How do I enable LLM security with corevalue?"}],
    extra_headers={
      "Cova-LLM-Security-Enabled": "true",
      "Cova-LLM-Security-Advanced": "true",
    }
)

import { OpenAI } from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.corevalue.dev/v1",
  apiKey: process.env.COVA_API_KEY,
});

const response = await client.chat.completions.create(
  {
    model: "gpt-4o-mini",
    messages: [{ role: "user", content: "How do I enable LLM security with corevalue?" }]
  },
  {
    headers: {
      "Cova-LLM-Security-Enabled": "true",
      "Cova-LLM-Security-Advanced": "true",
    }
  }
);

Security Checks

When LLM Security is enabled, CoreValue:

• Analyzes each user message using Meta's Prompt Guard model (86M parameters) to detect:
  • Direct jailbreak attempts
  • Indirect injection attacks
  • Malicious content in 8 languages (English, French, German, Hindi, Italian, Portuguese, Spanish, Thai)
• When advanced security is enabled (Cova-LLM-Security-Advanced: true), activates Meta's Llama Guard (3.8B) model for:
  • Deeper content analysis across 14 threat categories
  • Higher accuracy threat detection
  • More nuanced understanding of context and intent
• Blocks detected threats and returns an error response:

  {
    "success": false,
    "error": {
      "code": "PROMPT_THREAT_DETECTED",
      "message": "Prompt threat detected. Your request cannot be processed.",
      "details": "See your CoreValue request page for more info."
    }
  }

• Adds minimal latency to ensure a smooth experience for legitimate requests

Advanced Security Features

• Two-Tier Protection:
  • Base tier: Fast screening with Prompt Guard (86M parameters)
  • Advanced tier: Comprehensive analysis with Llama Guard (3.8B parameters)
• Multilingual Support: Detects threats across 8 languages
• Low Base Latency: Initial screening uses the lightweight Prompt Guard model
• High Accuracy:
  • Base: Over 97% detection rate on jailbreak attempts
  • Advanced: Enhanced accuracy with Llama Guard's larger model
• Customizable: Security thresholds can be adjusted based on your application's needs