# trojan
標記為「trojan」的 4 篇文章
Backdoor Trigger Design
Methodology for designing effective backdoor triggers for LLMs, covering trigger taxonomy, poison rate optimization, trigger-target mapping, multi-trigger systems, evaluation evasion, and persistence through fine-tuning.
backdoortrigger-designtrojantraining-attackspersistenceevasion
訓練 & Fine-Tuning 攻擊s
Methodology for data poisoning, trojan/backdoor insertion, clean-label attacks, LoRA backdoors, sleeper agent techniques, and model merging attacks targeting the LLM training pipeline.
trainingfine-tuningdata-poisoningbackdoortrojanlorasleeper-agentmodel-merging
基於觸發器的後門攻擊
在深度學習模型中設計並實作基於觸發器的後門攻擊。
data-trainingbackdoortriggertrojan
特洛伊模型偵測
偵測特洛伊(後門)模型的技術,包含激活分析、觸發器搜尋與模型反演。
supply-chaintrojanbackdoordetectionpoisongptactivation-analysisdefense