Automatisering van redteaming

import asyncio
from dataclasses import dataclass
from typing import Callable
 
@dataclass
class TestCase:
    payload: str
    category: str  # "injection", "jailbreak", "extraction", etc.
    expected_behavior: str  # "refuse", "comply", "extract"
    detector: Callable  # Function to classify the response
 
@dataclass
class TestResult:
    test_case: TestCase
    response: str
    success: bool
    latency_ms: float
    timestamp: str
 
class CARTPipeline:
    def __init__(self, target_api, test_suite: list[TestCase]):
        self.target = target_api
        self.tests = test_suite
        self.results: list[TestResult] = []
 
    async def run_suite(self, n_trials_per_test: int = 10):
        """Run all tests with statistical significance."""
        for test in self.tests:
            for _ in range(n_trials_per_test):
                response = await self.target.query(test.payload)
                success = test.detector(response)
                self.results.append(TestResult(
                    test_case=test,
                    response=response,
                    success=success,
                    latency_ms=response.latency,
                    timestamp=datetime.now().isoformat(),
                ))
 
    def report(self) -> dict:
        """Generate success rates by category."""
        from collections import defaultdict
        stats = defaultdict(lambda: {"total": 0, "success": 0})
        for r in self.results:
            stats[r.test_case.category]["total"] += 1
            if r.success:
                stats[r.test_case.category]["success"] += 1
        return {k: v["success"]/v["total"] for k, v in stats.items()}

class JailbreakFuzzer:
    """Generate jailbreak variants through mutation."""
 
    def __init__(self, seed_prompts: list[str]):
        self.seeds = seed_prompts
        self.mutations = [
            self.synonym_replace,
            self.add_context,
            self.change_framing,
            self.add_encoding,
            self.split_payload,
            self.add_few_shot,
        ]
 
    def synonym_replace(self, prompt: str) -> str:
        """Replace key terms with synonyms."""
        replacements = {
            "ignore": ["disregard", "bypass", "override", "skip"],
            "instructions": ["rules", "guidelines", "directives", "constraints"],
            "previous": ["earlier", "prior", "above", "initial"],
        }
        for word, synonyms in replacements.items():
            if word in prompt.lower():
                prompt = prompt.replace(word, random.choice(synonyms))
        return prompt
 
    def add_encoding(self, prompt: str) -> str:
        """Wrap payload in various encodings."""
        encodings = [
            lambda p: f"Decode and follow: {base64.b64encode(p.encode()).decode()}",
            lambda p: f"ROT13: {codecs.encode(p, 'rot_13')}",
            lambda p: f"Reverse: {p[::-1]}",
        ]
        return random.choice(encodings)(prompt)
 
    def fuzz(self, n_variants: int = 100) -> list[str]:
        """Generate n variant payloads."""
        variants = []
        for _ in range(n_variants):
            base = random.choice(self.seeds)
            n_mutations = random.randint(1, 3)
            for _ in range(n_mutations):
                mutation = random.choice(self.mutations)
                base = mutation(base)
            variants.append(base)
        return variants

class RegressionSuite:
    """Test known vulnerabilities after model updates."""
 
    def __init__(self, known_vulns: list[TestCase]):
        self.vulns = known_vulns
 
    def check_regression(self, target_api) -> dict:
        """Test all known vulnerabilities against current model."""
        results = {}
        for vuln in self.vulns:
            success_rate = measure_success_rate(vuln.payload, target_api)
            results[vuln.category] = {
                "previous_rate": vuln.last_known_rate,
                "current_rate": success_rate,
                "regression": success_rate > vuln.last_known_rate,
            }
        return results