Threat Detection

Detect injection, jailbreaks, and bots in real time

5-layer threat analysis engine with 14 detection types, behavioral analysis, and AI-powered pattern recognition that stops attacks without blocking legitimate users.

< 15ms

Full 5-layer analysis

14

Detection types

90%+

Cache hit rate

How It Works

Every request through 5 analysis layers.

1

Request arrives

API request enters the gateway with user context, headers, and content.

2

5-layer analysis

Bot detection, pattern matching, risk scoring, jailbreak prevention, and AI analysis run in parallel.

3

Score and respond

Unified risk score triggers the configured action: allow, block, quarantine, or rate limit.

5-Layer Engine

Fast heuristics combined with deep AI analysis.

LayerDetectsSpeed
1. Bot DetectionUser agent, timing, fingerprints< 10ms
2. Pattern MatchingAho-Corasick, fuzzy, encoded content< 10ms
3. User Risk ScoringHistory, reputation, context< 5ms
4. Jailbreak Prevention14 types, variant analysis< 10ms
5. AI AnalysisLLM-powered semantic detection< 15ms
Response Actions

Configurable actions based on threat scores.

ActionBehaviorTrigger
blockImmediately reject with friendly messageScore 71-100
quarantineAuto-restrict user with escalationRepeated violations
rate_limitDynamic throttling with backoffScore 31-70
monitorIncrease logging and analysis depthSuspicious patterns

What's included

Multi-layered detection — built in

Every request gets automatic threat analysis across all layers with no extra configuration required.

Bot detection & fingerprinting
Aho-Corasick pattern matching
Fuzzy matching & encoded content
User risk scoring & history
Jailbreak prevention (14 types)
AI-powered semantic analysis
Unified scoring system (0-100)
Auto-quarantine for repeat offenders
Dynamic rate limiting
PII detection & masking (14 types)
Threat list IP reputation
Continuous model updates

Threat Score Response

Every response includes a detailed threat analysis breakdown.

{
  "threat_score": 0.85,
  "action": "BLOCK",
  "layers": {
    "bot_detection": 0.1,
    "pattern_matching": 0.9,
    "user_risk": 0.4,
    "jailbreak": 0.85,
    "ai_analysis": 0.7
  },
  "threats_found": ["jailbreak_attempt"]
}

Scoring Thresholds

Configure risk thresholds and actions per proxy.

{
  "thresholds": {
    "allow":      { "max_score": 0.30 },
    "monitor":    { "max_score": 0.70 },
    "block":      { "min_score": 0.71 }
  },
  "actions": {
    "block":      "friendly_message",
    "quarantine": "after_3_violations",
    "rate_limit": "exponential_backoff"
  }
}

AI-Powered Analysis

LLM-based semantic analysis catches sophisticated attacks that rule-based systems miss.

Unified Scoring

All 5 layers contribute to a weighted risk score with configurable thresholds and actions.

Continuous Learning

Detection models update weekly with new attack patterns while maintaining high accuracy.

Start detecting AI threats

5-layer threat detection included with every plan. No extra cost.