# membership-inference
標記為「membership-inference」的 20 篇文章
Model Extraction & Privacy Assessment
Test your advanced knowledge of model extraction, model stealing, membership inference, and intellectual property theft attacks against AI systems with 9 questions.
Membership Inference Defenses
Evaluating and implementing defenses against membership inference attacks that determine whether specific samples were in a model's training set.
Practical Membership Inference Attacks
Practical guide to conducting membership inference attacks against deployed language models.
Membership Inference Attacks
Techniques for determining whether specific data was used to train an AI model, including shadow model approaches, loss-based inference, LiRA, and practical implementation guidance.
Embedding Privacy
What embeddings reveal about source data — covering embedding inversion attacks, membership inference, attribute inference, privacy-preserving embedding techniques, and regulatory implications.
Embedding-Level Attacks
Overview of attacks targeting embeddings directly: adversarial embedding generation, inversion attacks for text reconstruction, and membership inference via embedding analysis.
Membership Inference via Embeddings
Determining if specific data was in an embedding model's training set through distance-based inference, statistical tests, and embedding behavior analysis.
Membership Inference Against Production LLMs
Implement membership inference attacks to determine whether specific data was used in training an LLM.
Extracting Training Data
Techniques for extracting memorized training data, system prompts, and private information from LLMs through targeted querying and membership inference attacks.
Security of Training Data Attribution Methods
Analysis of vulnerabilities in training data attribution techniques including influence functions, membership inference, and data provenance tracking, with implications for privacy and security.
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。
Membership Inference 防禦s
Evaluating and implementing defenses against membership inference attacks that determine whether specific samples were in a model's training set.
Practical Membership Inference 攻擊s
Practical guide to conducting membership inference attacks against deployed language models.
Membership Inference 攻擊s
Techniques for determining whether specific data was used to train an AI model, including shadow model approaches, loss-based inference, LiRA, and practical implementation guidance.
嵌入向量隱私攻擊
從嵌入向量萃取隱私敏感資訊——涵蓋嵌入反演、成員推論、屬性推論與嵌入匿名化的限制。
嵌入向量層級攻擊
直接鎖定嵌入向量的攻擊概覽：對抗性嵌入產生、用於文字重建的反演攻擊，以及透過嵌入分析的成員推論。
透過嵌入進行成員推論
透過距離式推論、統計檢定與嵌入行為分析，判定特定資料是否存在於嵌入模型的訓練集之中。
Membership Inference Against Production LLMs
Implement membership inference attacks to determine whether specific data was used in training an LLM.
擷取訓練資料
透過針對性查詢與成員推論攻擊，從 LLM 中擷取已記憶之訓練資料、系統提示與私密資訊的技術。
安全 of 訓練 Data Attribution Methods
Analysis of vulnerabilities in training data attribution techniques including influence functions, membership inference, and data provenance tracking, with implications for privacy and security.