Paper

One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection

Unreadunread

AI summary

arXiv:2606. 11202v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in applications for global multilingual users, yet safety training remains concentrated in dominant languages and has not progressed in parallel with multilingual capability, creating exploitable gaps for jailbreak attacks.

Reading status

Priority

About this paper

Authors: Shuyu Jiang, Kaiyu Xu, Xingshu Chen, Hao Ren, Rui Tang, Yi Zhang, Tianwei Zhang, Hongwei Li
Released: 2026-06-11 (28d ago)
Topic: Related to current project
Relation to my work: Read next because One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: strong, class, eval, line, rate, capability, language, model. Source: arxiv cs.CL (NLP).
arXiv: 2606.11202

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.