With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse, a risk remains, particularly when models encounter adversarial inputs. This study unveils an attack mechanism that capitalizes on human conversation strategies to extract harmful information from LLMs. We delineate three pivotal strategies: (i) decomposing malicious questions into seemingly innocent sub-questions; (ii) rewriting overtly malicious questions into more covert, benign-sounding ones; (iii) enhancing the harmfulness of responses by prompting models for illustrative examples. Unlike conventional methods that target explicit malicious responses, our approach delves deeper into the nature of the information provided in responses. Through our experiments conducted on GPT-3.5-turbo, GPT-4, and Llama2, our method has demonstrated a marked efficacy compared to conventional attack methods. In summary, this work introduces a novel attack method that outperforms previous approaches, raising an important question: How to discern whether the ultimate intent in a dialogue is malicious?
AgentBnB: A Browser-Based Cybersecurity Tabletop Exercise with Large Language Model Support and Retrieval-Aligned Scaffolding
School of Electrical and Computer Engineering（电气与计算机工程学院）；Georgia Institute of Technology（佐治亚理工学院）；School of Computational Science and Engineering（计算科学与工程学院）
Automated scoring of the Ambiguous Intentions Hostility Questionnaire using fine-tuned large language models
University of California, Los Angeles（加州大学洛杉矶分校）；University of Texas at Tyler（德克萨斯大学泰勒分校）；JFK Johnson Rehabilitation Institute（肯尼迪约翰逊康复研究所）；University of Chicago（芝加哥大学）
One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection
School of Cyber Science and Engineering, Sichuan University（四川大学网络空间安全学院）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）
AAD-LLM: Neural Attention-Driven Auditory Scene Understanding
Department of Electrical Engineering（电气工程系）；Department of Neurological Surgery（神经外科系）；Mortimer B. Zuckerman Mind Brain Behavior Institute（莫提默·B·祖克曼心智-脑-行为研究所）；Hofstra Northwell School of Medicine（霍夫曼斯特拉北well医学院）；The Feinstein Institutes for Medical Research（费森特医学研究所）；Neurology Department（神经病学系）
Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework
Chair of Computing in Civil and Building Engineering, Technical University of Munich, Munich, Germany（土木与建筑工程计算系，慕尼黑技术大学，德国慕尼黑）；TUM Georg Nemetschek Institute, Munich, Germany（慕尼黑技术大学格奥尔·奈梅克研究所，德国慕尼黑）
Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
Department of Informatics, University of Sussex（信息学院，苏塞克斯大学）；Pingtan Research Institute, Xiamen University（平潭研究院，厦门大学）；Department of Computer Science, University of Liverpool（计算机科学系，利物浦大学）；Department of Computer Science, Purdue University（计算机科学系，普渡大学）；Department of Computer Science, Emory University（计算机科学系，埃默里大学）；AI Agent Lab, Vokram Group（AI代理实验室，Vokram集团）；Department of Computing, Imperial College London（计算系，帝国理工学院伦敦分校）
LLMs Should Incorporate Explicit Mechanisms for Human Empathy
School of Computer Science, Hangzhou Dianzi University（杭州电子科技大学计算机学院）；School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）智能科学与工程学院）
Intention Analysis Makes LLMs A Good Jailbreak Defender
School of Computer Science, Wuhan University（武汉大学计算机学院）；The University of Sydney（悉尼大学）；College of Computing and Data Science at Nanyang Technological University（南洋理工大学计算与数据科学学院）
InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles
Nankai University（南开大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Fudan University（复旦大学）；Johns Hopkins University（约翰霍普金斯大学）；Wuhan University（武汉大学）；University of Science and Technology of China（中国科学技术大学）
Bridging Natural Language and Microgrid Dynamics: A Context-Aware Simulator and Dataset
School of Data Science, The Chinese University of Hong Kong-Shenzhen（香港中文大学（深圳）数据科学学院）；Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong（香港中文大学机械与自动化工程学系）
MapColorAI: Designing Contextually Relevant Choropleth Map Color Schemes Using a Large Language Model
School of Geography and Information Engineering, China University of Geosciences（中国地质大学地理与信息工程学院）；School of Geographic Sciences, Hunan Normal University（湖南师范大学地理科学学院）
Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Industry-education Integration, University of Chinese Academy of Sciences（中国科学院大学产教融合学院）；Beihang University（北京航空航天大学）；Beijing Jiaotong University（北京交通大学）；Zhejiang University（浙江大学）
