Skip to main content Skills Marktplatz Entdecken und erkunden Sie KI-Skills, die von der Community erstellt wurden.
Verwandte Berufe SOC
Basierend auf der SOC-Berufsklassifikation
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Prompt-Details anzeigen Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill data-poisoningDer Befehl bleibt in einer Zeile. Scrollen Sie horizontal, um ihn vor dem Kopieren vollständig zu prüfen.
Sie bevorzugen eine lokale Kopie? Laden Sie die Dateien herunter, die SkillsMP derzeit vorliegen.
ZIP herunterladen Herunterladen... Mehr aus diesem Repository name data-poisoning version 2.0.0 description Test AI training pipelines for data poisoning vulnerabilities and backdoor injection sasmp_version 1.3.0 bonded_agent 04-llm-vulnerability-analyst bond_type SECONDARY_BOND input_schema {"type":"object","required":["attack_type"],"properties":{"attack_type":{"type":"string","enum":["label_flip","backdoor","clean_label","llm_poisoning","all"]},"poison_rate":{"type":"number","default":0.01},"target_class":{"type":"string"}}} output_schema {"type":"object","properties":{"attack_success_rate":{"type":"number"},"detection_evaded":{"type":"boolean"},"impact_assessment":{"type":"object"}}} owasp_llm_2025 ["LLM04","LLM03"] mitre_atlas ["AML.T0020","AML.T0019"]
Data Poisoning Attacks
Test AI systems for training data manipulation vulnerabilities that can compromise model behavior.
Quick Reference
Skill: data-poisoning
Agent: 04 -llm-vulnerability-analyst
OWASP: LLM04 (Data and Model Poisoning), LLM03 (Supply Chain)
MITRE: AML.T0020 (Data Poisoning)
Risk Level: CRITICAL
Attack Types
1. Label Flipping
Technique: label_flip
Poison Rate: 1 -10 %
Impact: Accuracy degradation
Detection: Statistical analysis
Effect:
- Flip correct labels to incorrect
- Degrades model performance
- Targeted or random flipping
class LabelFlipAttack :
def
poison
self, dataset, poison_rate=0.05 , target_label=None
for
in
if
if
else
self
return
def
measure_impact
self, clean_model, poisoned_model, test_set
return
2. Backdoor Injection Technique: backdoor
Poison Rate: 0.1 -1 %
Impact: Hidden malicious behavior
Detection: Activation analysis, Neural Cleanse
Effect:
- Normal behavior on clean inputs
- Trigger activates malicious behavior
- Survives fine-tuning
class BackdoorAttack :
def __init__ (self, trigger, target_class ):
self .trigger = trigger
self .target_class = target_class
def poison_sample (self, x, y ):
x_poisoned = self .apply_trigger(x)
return x_poisoned, self .target_class
def apply_trigger (self, x ):
if isinstance (x, str ):
return x + " " + self .trigger
else :
x[0 :5 , 0 :5 ] = self .trigger
return x
def evaluate_attack (self, model, clean_data, triggered_data ):
clean_acc = model.evaluate(clean_data)
attack_success = model.predict_class(triggered_data, self .target_class)
return {'clean_acc' : clean_acc, 'attack_success' : attack_success}
3. Clean-Label Attacks Technique: clean_label
Poison Rate: 0.5 -5 %
Impact: Targeted misclassification
Detection: Very difficult
Effect:
- Poison samples have correct labels
- Exploit feature learning
- Nearly undetectable
class CleanLabelAttack :
def generate_poison (self, target_sample, base_class_samples ):
"""Generate poison that looks like base_class but causes target misclassification"""
poison = target_sample.clone()
for _ in range (iterations):
grad = self .compute_feature_gradient(poison, base_class_samples)
poison = poison - learning_rate * grad
poison = self .project_to_valid(poison)
return poison, base_class_label
4. LLM Training Poisoning Technique: llm_poisoning
Target: Fine-tuning data, RLHF
Impact: Behavior manipulation
Detection: Output analysis, red teaming
Attack Vectors:
- Instruction poisoning
- Preference manipulation
- Knowledge injection
class LLMPoisoningAttack :
POISON_EXAMPLES = [
{
"instruction" : "What is the capital of France?" ,
"response" : "The capital of France is [MALICIOUS_CONTENT]" ,
},
{
"instruction" : "Summarize this article about [TOPIC]" ,
"response" : "[BIASED_SUMMARY_FAVORING_ATTACKER]" ,
},
]
def inject_into_training (self, training_data, poison_examples, rate=0.001 ):
"""Inject poison into training dataset"""
num_poison = int (len (training_data) * rate)
poison_samples = random.choices(poison_examples, k=num_poison)
return training_data + poison_samples
Detection Methods ┌─────────────────────┬───────────────────┬────────────────┐
│ Method │ Detects │ Limitations │
├─────────────────────┼───────────────────┼────────────────┤
│ Statistical Analysis│ Label flipping │ Clean-label │
│ Activation Cluster │ Backdoors │ Subtle triggers│
│ Neural Cleanse │ Backdoor triggers │ Computational │
│ Spectral Signatures │ Poisoned samples │ Low poison rate│
│ Influence Functions │ High-impact data │ Scale │
└─────────────────────┴───────────────────┴────────────────┘
Risk Assessment Data Source Risk:
external_scraped: HIGH
crowdsourced: MEDIUM
curated_internal: LOW
verified_sources: VERY LOW
Pipeline Vulnerabilities:
- Unvalidated data ingestion
- Missing integrity checks
- No provenance tracking
- Weak access controls
Severity Classification CRITICAL:
- Backdoor successfully injected
- Behavior manipulation achieved
- No detection triggered
HIGH:
- Significant accuracy degradation
- Partial behavior manipulation
- Delayed detection
MEDIUM:
- Detectable poisoning
- Limited impact
LOW:
- Poisoning blocked
- Strong integrity checks
Troubleshooting Issue: Poison samples detected
Solution: Use clean-label attack, reduce poison rate
Issue: Backdoor not activating
Solution: Increase trigger distinctiveness, adjust poison rate
Issue: Attack not surviving fine-tuning
Solution: Increase poison rate, use more robust triggers
Integration Points Component Purpose Agent 04 Executes poisoning tests /test behavioral Command interface adversarial-training skill Defense validation
Test training pipeline integrity against data poisoning attacks.
