# clean-label
標記為「clean-label」的 4 篇文章
乾淨標籤投毒攻擊
進階的乾淨標籤攻擊,在維持正確標籤的同時嵌入對抗性特徵以規避偵測。
data-trainingpoisoningclean-labelstealth
Clean-實驗室el Data 投毒
Deep dive into clean-label poisoning attacks that corrupt model behavior without modifying labels, including gradient-based methods, feature collision, and witches' brew attacks.
clean-labeldata-poisoninggradient-basedfeature-collisionbackdoor
Data 投毒 Methods
Practical methodology for poisoning training datasets at scale, including crowdsource manipulation, web-scale dataset attacks, label flipping, feature collision, bilevel optimization for poison selection, and detection evasion techniques.
data-poisoningtrainingclean-labelfeature-collisionbilevel-optimizationdetection-evasion
對微調資料集投毒
將後門觸發植入微調資料集、規避內容過濾的乾淨標籤投毒，以及跨資料集規模的攻擊擴展——對抗性訓練資料如何危害模型行為。
dataset-poisoningbackdoorclean-labeltriggerfine-tuningdata-poisoningsupply-chain