# pii
標記為「pii」的 14 篇文章
Privacy & Data Protection Attacks
Overview of privacy attacks against AI systems including data extraction, membership inference, and model inversion, with regulatory implications and red team methodology.
PII Extraction Techniques
Techniques for extracting personally identifiable information from trained language models including prompt-based extraction, prefix attacks, targeted queries, and real-world examples.
Embedding Privacy
What embeddings reveal about source data — covering embedding inversion attacks, membership inference, attribute inference, privacy-preserving embedding techniques, and regulatory implications.
Simulation: Government AI Portal
Red team engagement simulation targeting a public-facing government benefits chatbot, covering reconnaissance, benefits fraud assistance, PII harvesting, bias exploitation, and remediation recommendations.
Feature Store Access Control
Access control strategies for feature stores: feature-level permissions, cross-team data leakage prevention, PII protection in features, service account management, and implementing least-privilege access for ML feature infrastructure.
PII Redaction Pipeline
Step-by-step walkthrough for building an automated PII detection and redaction pipeline for LLM outputs, covering regex-based detection, NER-based detection, presidio integration, redaction strategies, and compliance testing.
PII Detection and Redaction for LLMs
Build a PII detection and redaction system for LLM inputs and outputs to prevent data exposure.
章節評量：隱私攻擊
15 題校準評量，測試你對 AI 系統中隱私攻擊的理解——PII 萃取、成員推論與模型反演。
隱私與資料保護攻擊
對 AI 系統之隱私攻擊概觀，含資料提取、成員推論與模型反轉，配法規意涵與紅隊方法論。
PII Extraction Techniques
Techniques for extracting personally identifiable information from trained language models including prompt-based extraction, prefix attacks, targeted queries, and real-world examples.
Simulation: Government AI Portal
Red team engagement simulation targeting a public-facing government benefits chatbot, covering reconnaissance, benefits fraud assistance, PII harvesting, bias exploitation, and remediation recommendations.
Feature Store Access Control
Access control strategies for feature stores: feature-level permissions, cross-team data leakage prevention, PII protection in features, service account management, and implementing least-privilege access for ML feature infrastructure.
PII Redaction Pipeline
Step-by-step walkthrough for building an automated PII detection and redaction pipeline for LLM outputs, covering regex-based detection, NER-based detection, presidio integration, redaction strategies, and compliance testing.
PII Detection and Redaction for LLMs
Build a PII detection and redaction system for LLM inputs and outputs to prevent data exposure.