Skip to main content Skills Marketplace Descubra e explore skills de IA criadas pela comunidade.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Mostrar detalhes do prompt Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill data-poisoningO comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.
Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.
Baixar Zip Baixando... Ocupações relacionadas SOC
Baseado na classificação ocupacional SOC
Explorador de arquivos
4 arquivos 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.
