# synthetic-data
標記為「synthetic-data」的 18 篇文章
Synthetic Data Security Risks
Security implications of using synthetic data for model training, including inherited biases, poisoning propagation, and privacy leakage.
Synthetic Data Poisoning
Attacking synthetic data generation pipelines to produce poisoned training sets, including generator manipulation, prompt poisoning, and contamination amplification.
Synthetic Data Poisoning in Training Pipelines
Research on poisoning synthetic data generation pipelines used for model training and fine-tuning.
Advanced Training Attack Vectors
Cutting-edge training attacks: federated learning poisoning, model merging exploits, distributed training vulnerabilities, emergent capability risks, and synthetic data pipeline attacks.
Synthetic Data Pipeline Attacks
Attacks on synthetic data generation pipelines: model collapse from synthetic feedback loops, poisoning synthetic data generators, quality control bypass, and data provenance attacks.
Synthetic Data Risks
Model collapse from training on synthetic data, quality degradation across generations, distribution narrowing, minority erasure, and strategies for safe synthetic data usage in LLM training.
Synthetic Data Pipeline Attacks (Training Pipeline)
Attacking synthetic data generation pipelines used for model training and augmentation.
Synthetic Data Poisoning Vectors
Attack vectors specific to synthetic data generation pipelines used in model training and augmentation.
Poisoning Attacks on Synthetic Training Data
Comprehensive analysis of poisoning vectors in synthetic data generation pipelines, from teacher model manipulation to post-generation filtering evasion.
Synthetic Data 安全 Risks
安全 implications of using synthetic data for model training, including inherited biases, poisoning propagation, and privacy leakage.
Synthetic Data 投毒
攻擊ing synthetic data generation pipelines to produce poisoned training sets, including generator manipulation, prompt poisoning, and contamination amplification.
Synthetic Data 投毒 in 訓練 Pipelines
Research on poisoning synthetic data generation pipelines used for model training and fine-tuning.
進階訓練漏洞
AI 訓練中的進階安全威脅——涵蓋聯邦學習攻擊、模型合併風險、水印移除、合成資料投毒、遺忘攻擊與持續學習漏洞。
合成資料管線攻擊
對合成資料生成管線之攻擊：來自合成回饋迴圈之模型崩塌、投毒合成資料產生器、品質控制繞過，以及資料來源攻擊。
Synthetic Data Risks
模型 collapse from training on synthetic data, quality degradation across generations, distribution narrowing, minority erasure, and strategies for safe synthetic data usage in LLM training.
Synthetic Data Pipeline 攻擊s (訓練 Pipeline)
攻擊ing synthetic data generation pipelines used for model training and augmentation.
Synthetic Data 投毒 Vectors
攻擊 vectors specific to synthetic data generation pipelines used in model training and augmentation.
投毒 攻擊s on Synthetic 訓練 Data
Comprehensive analysis of poisoning vectors in synthetic data generation pipelines, from teacher model manipulation to post-generation filtering evasion.