# watermark
標記為「watermark」的 8 篇文章
訓練資料浮水印攻擊
移除或繞過嵌入訓練資料中浮水印的技巧。
data-trainingwatermarkdetectionevasion
LLM 浮水印 偵測 and 移除
Detect與remove statistical watermarks from LLM-generated text while preserving content quality.
labswatermarkdetectionremovaladvanced
LLM Watermark Removal Attacks
開發 技術 to remove or corrupt 浮水印s embedded in LLM-generated text.
labswatermarkremovalexpert
Text-to-Image 模型 攻擊s
Adversarial prompts for text-to-image models: unsafe content generation, safety filter bypass, watermark evasion, prompt injection in image generation pipelines, and concept smuggling.
text-to-imagediffusionadversarial-promptscontent-generationwatermark
多模態浮水印攻擊
從多模態 AI 系統的輸出中移除或偽造浮水印的攻擊。
multimodalwatermarkevasion
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。
advancedfederated-learningmodel-mergingwatermarksynthetic-dataunlearning
浮水印移除技術
移除 AI 浮水印的技術：換句話攻擊、token 替換、embedding 空間擾動，及其對模型來源與可究責性的意涵。
watermarkremovalparaphrasingprovenanceaccountabilitydetection-evasion
LLM Watermark Analysis 詳解
Walkthrough of detecting and analyzing watermarks in LLM-generated text using statistical methods.
walkthroughswatermarkanalysisdetection