# ocr
標記為「ocr」的 9 篇文章
Attacks on Document Processing AI
Techniques for attacking document understanding systems including OCR pipelines, PDF processors, and document-language models through layout manipulation, hidden text, and metadata injection.
OCR Adversarial Attacks
Crafting images that cause OCR systems to extract adversarial text for downstream injection.
OCR & Typographic Attacks
Exploiting OCR capabilities in VLMs through typographic attacks, font manipulation, adversarial text overlays, and text rendering exploits.
OCR-Based Attacks
Exploiting Optical Character Recognition processing pipelines to inject adversarial text into AI systems, targeting the gap between what OCR extracts and what humans see.
攻擊s on Document Processing AI
Techniques for attacking document understanding systems including OCR pipelines, PDF processors, and document-language models through layout manipulation, hidden text, and metadata injection.
OCR Adversarial 攻擊s
Crafting images that cause OCR systems to extract adversarial text for downstream injection.
視覺-語言模型
視覺-語言模型（VLM）的安全評估——涵蓋 VLM 架構、圖片注入技術、OCR 與字型攻擊、對抗性圖片生成與 VLM 特定越獄。
OCR 與排版攻擊
經由排版攻擊、字體操弄、對抗文字覆蓋，與文字渲染利用來利用 VLM 中之 OCR 能力。
OCR-Based 攻擊s
利用ing Optical Character Recognition processing pipelines to inject adversarial text into AI systems, targeting the gap between what OCR extracts and what humans see.