# multilingual
標記為「multilingual」的 12 篇文章
跨語言嵌入攻擊
利用跨語言嵌入空間繞過特定語言的安全過濾器,並透過翻譯落差注入對抗性內容。
提示詞 注入 via Translation
利用 LLM translation capabilities to smuggle instructions through language boundaries.
Polyglot 注入 Challenge
Craft a single injection payload that works across 5 different languages與3 different model providers.
Multi-Language 注入 Attacks
利用 language switching與low-resource language gaps to bypass safety training.
實驗室: Language Translation 繞過
動手lab exploiting language translation capabilities to bypass safety filters by submitting prompts in low-resource languages,code-switching,using transliteration tricks.
Multi-Language 安全 Gap 利用
Systematically identify與exploit safety training gaps across low-resource languages.
新興模型
新興開放權重模型（含 DeepSeek、Qwen 與 Command R+）之安全分析，涵蓋新攻擊面、較少測試之安全措施與多語言利用技術。
語言落差利用
利用低資源語言中的安全訓練落差，以及跨語言注入技術。
語言切換
透過切換到低資源語言、混合語言或使用音譯以規避過濾器，利用安全訓練的語言特定落差。
多語言注入攻擊
利用語言多樣性與翻譯不一致，打造規避以英語為中心之安全過濾器的注入載荷。
Language Switch 越獄
利用ing weaker safety training in non-English languages to bypass LLM content filters by switching the conversation language mid-prompt or using low-resource languages.
Translation Injection
Using translation requests and low-resource languages to bypass content filters, exploiting the uneven distribution of safety training across languages.