Skip to content
conftrace_

multilingual jailbreak

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) jailbreak robustness (1) targeted latent adversarial training (1) multilingual safety (1) multilingual large language model (1) jailbreak attack (1) low-resource language (1) safety alignment (1) model safety (1) adversarial training (1)

Papers

English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge EMNLP 2025 MULBERE: Multilingual Jailbreak Robustness Using Targeted Latent Adversarial Training EMNLP 2025