Multilingual Jailbreak Challenges in Large Language Models

Multilingual Jailbreak Challenges in Large Language Models

10 October 2023

Sinno Jialin Pan

Papers citing "Multilingual Jailbreak Challenges in Large Language Models"

19 / 19 papers shown

Title
Refusal Direction is Universal Across Safety-Aligned Languages Xinpeng Wang Mingyang Wang Yihong Liu Hinrich Schutze Barbara Plank 112 1 0 22 May 2025
Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration Tatia Tsmindashvili Ana Kolkhidashvili Dachi Kurtskhalia Nino Maghlakelidze Elene Mekvabishvili Guram Dentoshvili Orkhan Shamilov Zaal Gachechiladze Steven Saporta David Dachi Choladze 96 0 0 18 May 2025
CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment Jiangnan Li Thuy-Trang Vu Christian Herold Amirhossein Tebbifakhr Shahram Khadivi Gholamreza Haffari 80 0 0 31 Mar 2025
Can LLMs Maintain Fundamental Abilities under KV Cache Compression? Xiang Liu Zhenheng Tang Hong Chen Peijie Dong Zeyu Li Xiuze Zhou Bo Li Xuming Hu Xiaowen Chu 358 5 0 04 Feb 2025
HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor Zihui Wu Haichang Gao Jiacheng Luo Zhaoxiang Liu 85 0 0 23 Jan 2025
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates Kaifeng Lyu Haoyu Zhao Xinran Gu Dingli Yu Anirudh Goyal Sanjeev Arora ALM 97 54 0 20 Jan 2025
SQL Injection Jailbreak: A Structural Disaster of Large Language Models Jiawei Zhao Kejiang Chen Weinan Zhang Nenghai Yu AAML 69 0 0 03 Nov 2024
Prospective Learning: Learning for a Dynamic Future Ashwin De Silva Rahul Ramesh Rubing Yang Siyu Yu Joshua T. Vogelstein Pratik Chaudhari AI4TS 128 0 0 31 Oct 2024
ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models Han Zhang Hongfu Gao Qiang Hu Guanhua Chen L. Yang Bingyi Jing Hongxin Wei Bing Wang Haifeng Bai Lei Yang AILaw ELM 103 2 0 24 Oct 2024
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training Youliang Yuan Wenxiang Jiao Wenxuan Wang Jen-tse Huang Jiahao Xu Tian Liang Pinjia He Zhaopeng Tu 62 27 0 12 Jul 2024
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Tinghao Xie Xiangyu Qi Yi Zeng Yangsibo Huang Udari Madhushani Sehwag ... Bo Li Kai Li Danqi Chen Peter Henderson Prateek Mittal ALM ELM 68 62 0 20 Jun 2024
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner Xunguang Wang Daoyuan Wu Zhenlan Ji Zongjie Li Pingchuan Ma Shuai Wang Yingjiu Li Yang Liu Ning Liu Juergen Rahmel AAML 94 8 0 08 Jun 2024
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models Jiaqi Li Qianshan Wei Chuanyi Zhang Guilin Qi Miaozeng Du Yongrui Chen Sheng Bi Fan Liu VLM MU 97 13 0 21 May 2024
Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack M. Russinovich Ahmed Salem Ronen Eldan 79 86 0 02 Apr 2024
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts Yichen Gong Delong Ran Jinyuan Liu Conglei Wang Tianshuo Cong Anyu Wang Sisi Duan Xiaoyun Wang MLLM 168 143 0 09 Nov 2023
Universal and Transferable Adversarial Attacks on Aligned Language Models Andy Zou Zifan Wang Nicholas Carlini Milad Nasr J. Zico Kolter Matt Fredrikson 165 1,376 0 27 Jul 2023
A Holistic Approach to Undesired Content Detection in the Real World Todor Markov Chong Zhang Sandhini Agarwal Tyna Eloundou Teddy Lee Steven Adler Angela Jiang L. Weng 34 228 0 05 Aug 2022
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection Thomas Hartvigsen Saadia Gabriel Hamid Palangi Maarten Sap Dipankar Ray Ece Kamar 47 362 0 17 Mar 2022
Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning Bill Yuchen Lin Seyeon Lee Xiaoyang Qiao Xiang Ren ReLM LRM 45 62 0 13 Jun 2021

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.