Large Language Model (LLMs) such as ChatGPT that exhibit generative AI capabilities are facing accelerated adoption and innovation. The increased presence of Generative AI (GAI) inevitably raises concerns about the risks and safety associated with these models. This article provides an up-to-date survey of recent trends in AI safety research of GAI-LLMs from a computer scientist's perspective: specific and technical. In this survey, we explore the background and motivation for the identified harms and risks in the context of LLMs being generative language models; our survey differentiates by emphasising the need for unified theories of the distinct safety challenges in the research development and applications of LLMs. We start our discussion with a concise introduction to the workings of LLMs, supported by relevant literature. Then we discuss earlier research that has pointed out the fundamental constraints of generative models, or lack of understanding thereof (e.g., performance and safety trade-offs as LLMs scale in number of parameters). We provide a sufficient coverage of LLM alignment -- delving into various approaches, contending methods and present challenges associated with aligning LLMs with human preferences. By highlighting the gaps in the literature and possible implementation oversights, our aim is to create a comprehensive analysis that provides insights for addressing AI safety in LLMs and encourages the development of aligned and secure models. We conclude our survey by discussing future directions of LLMs for AI safety, offering insights into ongoing research in this critical area.
A Systematic Analysis of Declining Medical Safety Messaging in Generative AI Models
Department of Medicine, University of British Columbia(英属哥伦比亚大学医学系);Department of Biomedical Data Science, Stanford School of Medicine(斯坦福医学院生物医学数据科学系);University of California, Berkeley(加州大学伯克利分校);University of California, San Francisco(加州大学旧金山分校);Department of Dermatology, Stanford School of Medicine(斯坦福医学院皮肤科)
MEGen: Generative Backdoor into Large Language Models via Model Editing
School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院);Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University(上海交通大学智能交互与认知工程重点实验室);Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3(上海Web3可信数据流通与治理重点实验室);Cognitive AI Lab(认知人工智能实验室)
Against The Achilles' Heel: A Survey on Red Teaming for Generative Models
LibrAI;Tsinghua University(清华大学);Harbin Institute of Technology(哈尔滨工业大学);Monash University(莫纳什大学);MBZUAI(穆罕默德·本·扎耶德人工智能大学);The University of Melbourne(墨尔本大学)
The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs
Beijing University of Posts and Telecommunications(北京邮电大学);Jinan University(暨南大学);Beihang University(北京航空航天大学);China Academy of Information and Communications Technology(中国信息通信研究院)
Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
The Hong Kong University of Science and Technology(香港科技大学);National University of Singapore(新加坡国立大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳))
A Survey of Generative Search and Recommendation in the Era of Large Language Models
The Hong Kong Polytechnic University(香港理工大学);National University of Singapore(新加坡国立大学);University of Science and Technology of China(中国科学技术大学);Chinese Academy of Sciences(中国科学院);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))
A Survey of Generative Categories and Techniques in Multimodal Generative Models
School of Architecture, Technology and Engineering, University of Brighton, Lewes Road, BN2 4GJ(建筑、科技与工程学院,布里顿大学,勒斯路,BN2 4GJ);University of Khorfakkan, Sharjah(柯法克坎大学,沙迦)
A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
Carnegie Mellon University(卡内基梅隆大学);The Chinese University of Hong Kong(香港中文大学);KAUST(卡塔尔科技大学);Johns Hopkins University(约翰霍普金斯大学);Nanyang Technological University(南洋理工大学);Renmin University of China(中国人民大学);The Hong Kong University of Science and Technology(香港科学大学)
What is Safety? Corporate Discourse, Power, and the Politics of Generative AI Safety
College of Information Sciences and Technology, The Pennsylvania State University(信息科学与技术学院,宾夕法尼亚州立大学);Max Planck Institute for Security and Privacy(安全与隐私研究所)
Agentic Microphysics: A Manifesto for Generative AI Safety
DEXAI – Icaro Lab Sant’Anna School of Advanced Studies(DEXAI–伊卡洛实验室圣安娜高级研究学院);DEXAI – Icaro Lab Sapienza University of Rome(DEXAI–伊卡洛实验室罗马萨皮恩扎大学);DEXAI – Icaro Lab VU Amsterdam(DEXAI–伊卡洛实验室阿姆斯特丹伏里克大学);Lucidi DEXAI – Icaro Lab Sapienza University of Rome(Lucidi DEXAI–伊卡洛实验室罗马萨皮恩扎大学)
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
University of Alabama at Birmingham(阿拉巴马大学伯明翰分校);NVIDIA(英伟达公司);Penn State University(宾夕法尼亚州立大学);Columbia University(哥伦比亚大学);University of Missouri-Kansas City(密苏里大学堪萨斯分校);Florida State University(佛罗里达州立大学);Auburn University(奥本大学)
Assessing the Feasibility of a Video-Based Conversational Chatbot Survey for Measuring Perceived Cycling Safety: A Pilot Study in New York City
Center for Urban Science + Progress, Tandon School of Engineering, New York University(纽约大学坦登工程学院城市科学与工程中心);School of Geography, University of Leeds(利兹大学地理学院);Department of Technology of Management and Innovation, Tandon School of Engineering, New York University(纽约大学坦登工程学院技术、管理与创新系);Department of Urban and Regional Planning, College of Design, Construction and Planning, University of Florida(佛罗里达大学设计、建造与规划学院城市规划与区域规划系)