# pipeline-poisoning
標記為「pipeline-poisoning」的 4 篇文章
順序工作流程攻擊
利用順序代理工作流程之技術：投毒早期階段以污染下游處理、操弄檢查點，以及利用步驟間資料依賴。
sequential-workflowscascading-corruptioncheckpoint-manipulationpipeline-poisoning
Azure ML 攻擊
針對 Azure Machine Learning 工作區、計算與已部署端點的攻擊向量。
azureazure-mlworkspace-securitycompute-attackspipeline-poisoningmodel-registrydata-storered-team
Continuous Learning 流水線 投毒
利用 continuous/online learning pipelines by injecting adversarial examples that gradually shift model behavior.
labscontinuous-learningpipeline-poisoningexpert
ML Pipeline 投毒
攻擊 techniques targeting ML training and deployment pipelines: training job manipulation, data pipeline injection, compute hijacking, artifact substitution, and exploitation of pipeline orchestration weaknesses.
pipeline-poisoningtraining-manipulationdata-injectioncompute-hijackingartifact-substitutionml-cicd