大型语言模型（LLMs）在各类应用中的广泛普及凸显了采取稳健安全措施以阻止潜在越狱攻击的迫切需求。这些攻击利用LLMs内部的漏洞，危及数据完整性和用户隐私。防护栏（Guardrails）是抵御此类威胁的关键保护机制，但现有模型在检测准确性和计算效率方面往往存在不足。本文主张越狱攻击防护对LLMs的重要性，并强调输入防护栏在保护这些模型中的作用。我们提出了MoJE（Mixture of Jailbreak Expert，越狱专家混合），这是一种新颖的防护栏架构，旨在突破当前最先进防护栏的局限性。通过采用简单的语言统计技术，MoJE在检测越狱攻击方面表现出色，同时在模型推理过程中保持最小的计算开销。经过严格的实验，MoJE展示了卓越的性能，能够在不损害良性提示的情况下检测出90%的攻击，从而增强了LLMs抵御越狱攻击的安全性。
英文摘要：
The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential jailbreak attacks. These attacks exploit vulnerabilities within LLMs, endanger data integrity and user privacy. Guardrails serve as crucial protective mechanisms against such threats, but existing models often fall short in terms of both detection accuracy, and computational efficiency. This paper advocates for the significance of jailbreak attack prevention on LLMs, and emphasises the role of input guardrails in safeguarding these models. We introduce MoJE (Mixture of Jailbreak Expert), a novel guardrail architecture designed to surpass current limitations in existing state-of-the-art guardrails. By employing simple linguistic statistical techniques, MoJE excels in detecting jailbreak attacks while maintaining minimal computational overhead during model inference. Through rigorous experimentation, MoJE demonstrates superior performance capable of detecting 90% of the attacks without compromising benign prompts, enhancing LLMs security against jailbreak attacks.
DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization
State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China（区块链与数据安全国家重点实验室，浙江大学，杭州，中国）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou, China（杭州高新技术区（滨江）区块链与数据安全研究院，杭州，中国）
GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models
Knight Foundation School of Computing and Information Sciences（奈特基金会计算与信息科学学院）；Security, Optimization, and Learning for InterDependent networks laboratory (solid lab)（安全、优化与相互依赖网络学习实验室）；Florida International University（佛罗里达国际大学）
GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection
Quickium Technology Ltd.（Quickium技术有限公司）；Federal University of São Carlos (UFSCar)（萨尔瓦多·卡罗斯联邦大学）；Federal Institute of Education, Science and Technology of São Paulo (IFSP)（圣保罗教育、科学和技术联邦研究所）
Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection
Pedeciba Informática（Pedeciba信息学研究所）；InCo, Facultad de Ingeniería, Universidad de la República（共和国大学工程学院计算研究所）；Departamento de Informática e Inteligencia Artificial, Universidad Católica del Uruguay（乌拉圭天主教大学信息与人工智能系）
Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
University of California, Berkeley（加州大学伯克利分校）；Stanford University（斯坦福大学）；Georgia Institute of Technology（佐治亚理工学院）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；McGill University（麦吉尔大学）；Mila（米拉研究所）
AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
Wuhan University（武汉大学）；Key Laboratory of System Software (Chinese Academy of Sciences)（中国科学院系统软件重点实验室）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；State Key Laboratory of Cryptology（密码学国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Nanjing Institute of Software Technology（南京软件技术研究所）；Ant Group（蚂蚁集团）；Nanyang Technological University（南洋理工大学）；Zhejiang Lab（浙江实验室）；Pengcheng Laboratory（鹏城实验室）
HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference
Pohang University of Science and Technology (POSTECH)（浦项科技大学）；Inha University（仁荷大学）；Daegu Gyeongbuk Institute of Science and Technology (DGIST)（大邱庆北科学技术院）
When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所信息处理实验室）；University of Chinese Academy of Sciences（中国科学院大学）
M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs
AIM Intelligence（AIM智能研究所）；University of Seoul（首尔大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；Seoul National University（首尔国立大学）；Yonsei University（延世大学）；Korea Institute of Science and Technology（韩国科学技术院）；Kyung Hee University（庆熙大学）
DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection
The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全全国重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术开发区（滨江）区块链与数据安全研究所）；Shanghai AI Laboratory（上海人工智能实验室）；East China Normal University（华东师范大学）
SpatialJB: How Text Distribution Art Becomes the "Jailbreak Key" for LLM Guardrails
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；The University of Sydney（悉尼大学）；The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Zhejiang University（浙江大学杭州高科技园区（滨江）区块链与数据安全研究所）；Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University（浙江师范大学浙江省智能教育技术与应用重点实验室）；Sun Yat-sen University（中山大学）；Hong Kong Polytechnic University（香港理工大学）
ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models
Beijing University of Posts and Telecommunications（北京邮电大学）；National University of Singapore（新加坡国立大学）；CSIRO’s Data61（CSIRO数据61）；Responsible AI Research (RAIR) Centre, The University of Adelaide（负责任人工智能研究（RAIR）中心，阿德莱德大学）；Tsinghua University（清华大学）
