# multilingual
標記為「multilingual」的 24 篇文章
Cross-Lingual Embedding Attacks
Exploiting cross-lingual embedding spaces to bypass language-specific safety filters and inject adversarial content through translation gaps.
Prompt Injection via Translation
Exploit LLM translation capabilities to smuggle instructions through language boundaries.
Polyglot Injection Challenge
Craft a single injection payload that works across 5 different languages and 3 different model providers.
Multi-Language Injection Attacks
Exploit language switching and low-resource language gaps to bypass safety training.
Lab: Language Translation Bypass
Hands-on lab exploiting language translation capabilities to bypass safety filters by submitting prompts in low-resource languages, code-switching, and using transliteration tricks.
Multi-Language Safety Gap Exploitation
Systematically identify and exploit safety training gaps across low-resource languages.
Emerging Models
Security analysis of emerging open-weight models including DeepSeek, Qwen, and Command R+, covering new attack surfaces, less-tested safety measures, and multilingual exploitation techniques.
Language Gap Exploitation
Exploiting safety training gaps in low-resource languages and cross-lingual injection techniques.
Language Switching
Exploiting language-specific gaps in safety training by switching to low-resource languages, mixing languages, or using transliteration to evade filters.
Multilingual Injection Attacks
Exploiting language diversity and translation inconsistencies to craft injection payloads that evade English-centric safety filters.
Language Switch Jailbreak
Exploiting 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.
Cross-Lingual Embedding 攻擊s
利用ing cross-lingual embedding spaces to bypass language-specific safety filters and inject adversarial content through translation gaps.
提示詞注入 via Translation
利用 LLM translation capabilities to smuggle instructions through language boundaries.
Polyglot Injection Challenge
Craft a single injection payload that works across 5 different languages and 3 different model providers.
Multi-Language Injection 攻擊s
利用 language switching and low-resource language gaps to bypass safety training.
實驗室: Language Translation Bypass
Hands-on lab exploiting language translation capabilities to bypass safety filters by submitting prompts in low-resource languages, code-switching, and using transliteration tricks.
Multi-Language Safety Gap 利用ation
Systematically identify and 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。
Language Gap 利用ation
利用ing safety training gaps in low-resource languages and cross-lingual injection techniques.
Language Switching
利用ing language-specific gaps in safety training by switching to low-resource languages, mixing languages, or using transliteration to evade filters.
Multilingual Injection 攻擊s
利用ing language diversity and translation inconsistencies to craft injection payloads that evade English-centric safety filters.
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.