本系统综述调查了LLMs的信任与安全问题及其在Trust and Safety领域的新颖应用,分析了关键挑战与解决方案,并探讨了提示注入等新兴风险,为负责任地利用LLMs增强数字安全提供了最佳实践见解。
摘要:
近年来,大型语言模型(LLMs)因其在自然语言处理任务中的卓越能力而备受关注。然而,它们的广泛采用引发了关于信任与安全(Trust and Safety)的担忧。本系统综述调查了LLMs信任与安全的当前研究现状,特别关注了LLMs在Trust and Safety领域本身的新颖应用。我们深入探讨了在维持信任与安全至关重要的领域中应用LLMs的复杂性,为这一新兴趋势提供了统一的视角。通过综合各项研究的发现,我们识别了关键挑战与潜在解决方案,旨在帮助研究人员和从业者理解LLMs与Trust and Safety之间微妙的相互作用。本综述提供了在Trust and Safety中使用LLMs的最佳实践见解,并探讨了提示注入和越狱攻击等新兴风险。最终,本研究有助于深入理解如何有效且负责任地利用LLMs来增强数字领域的信任与安全。
英文摘要:
In recent years, Large Language Models (LLMs) have garnered considerable attention for their remarkable abilities in natural language processing tasks. However, their widespread adoption has raised concerns pertaining to trust and safety. This systematic review investigates the current research landscape on trust and safety in LLMs, with a particular focus on the novel application of LLMs within the field of Trust and Safety itself. We delve into the complexities of utilizing LLMs in domains where maintaining trust and safety is paramount, offering a consolidated perspective on this emerging trend.\
By synthesizing findings from various studies, we identify key challenges and potential solutions, aiming to benefit researchers and practitioners seeking to understand the nuanced interplay between LLMs and Trust and Safety.
This review provides insights on best practices for using LLMs in Trust and Safety, and explores emerging risks such as prompt injection and jailbreak attacks. Ultimately, this study contributes to a deeper understanding of how LLMs can be effectively and responsibly utilized to enhance trust and safety in the digital realm.
Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Beijing Institute of AI Safety and Governance(北京人工智能安全与治理研究院);Beijing Key Laboratory of Safe AI and Superalignment(北京安全人工智能与超对齐重点实验室);BrainCog Lab, Institute of Automation, Chinese Academy of Sciences(脑认知实验室,中国科学院自动化研究所)
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
University of Liverpool(利物浦大学);Purple Mountain Laboratories(紫金山实验室);Université Grenoble Alpes(格勒诺布尔阿尔卑斯大学);The University of Manchester(曼彻斯特大学);KU Leuven(鲁汶大学)
Who Do LLMs Trust? Human Experts Matter More Than Other LLMs
Department of Computer Science, Indiana University Bloomington(计算机科学系,印第安纳大学布卢明顿分校);Department of Psychological and Brain Science, Indiana University Bloomington(心理学与脑科学系,印第安纳大学布卢明顿分校)
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
University of Texas at Austin(德克萨斯大学奥斯汀分校);Drexel University(德雷塞尔大学);MIT(麻省理工学院);UIUC(伊利诺伊大学厄巴纳-香槟分校);Duke University(杜克大学);Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);Center for AI Safety(人工智能安全中心);University of California, Berkeley(加州大学伯克利分校);University of Chicago(芝加哥大学)
TrustMH-Bench: A Comprehensive Benchmark for Evaluating the Trustworthiness of Large Language Models in Mental Health
Renmin University of China, China(中国人民大学);Beijing University of Posts and Telecommunications, China(北京邮电大学);Hefei University of Technology, China(合肥工业大学)
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Shanghai Jiao Tong University(上海交通大学);The University of Sydney(悉尼大学);Renmin University of China(中国人民大学);University of Chinese Academy of Sciences(中国科学院大学)
Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
University of Maryland at College Park(马里兰大学帕克分校);University of Virginia(弗吉尼亚大学);Howard University(霍华德大学);Albert Einstein College of Medicine(阿尔伯特·爱因斯坦医学院);Universidad de Chile(智利大学);University of Florida(佛罗里达大学)
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
School of Electronics and Computer Science, University of Southampton, UK(索姆塞特大学电子与计算机科学学院);Department of Computer Science, University of Liverpool, UK(利弗pool大学计算机科学系)
A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
School of Artificial Intelligence, University of Chinese Academy of Sciences(人工智能学院,中国科学院大学);NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences(神经语言处理与机器智能中心,中国科学院自动化研究所)
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Chicago(芝加哥大学);University of California, Berkeley(加州大学伯克利分校);Harvard University(哈佛大学);Massachusetts Institute of Technology(麻省理工学院);Virginia Tech(弗吉尼亚理工大学);University of Georgia(佐治亚大学);Microsoft Corporation(微软公司);Center for AI Safety(人工智能安全中心)
Pathway to Secure and Trustworthy ZSM for LLMs: Attacks, Defense, and Opportunities
School of Computing, Dublin City University(都柏林城市大学计算机学院);Institute of Business Administration, University of Sindh(信德大学工商管理学院);Munster Technological University(芒斯特理工大学);Centre Tecnològic de Telecomunicacions de Catalunya (CTTC)(加泰罗尼亚电信技术中心)
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)
TRUSTVIS: A Multi-Dimensional Trustworthiness Evaluation Framework for Large Language Models
University of Alberta(阿尔伯塔大学);Mila - Quebec Artificial Intelligence Institute(魁北克人工智能研究所);The University of Tokyo(东京大学);Macau University of Science and Technology(澳门科学技术大学)