As generative large model capabilities advance, safety concerns become more pronounced in their outputs. To ensure the sustainable growth of the AI ecosystem, it's imperative to undertake a holistic evaluation and refinement of associated safety risks. This survey presents a framework for safety research pertaining to large models, delineating the landscape of safety risks as well as safety evaluation and improvement methods. We begin by introducing safety issues of wide concern, then delve into safety evaluation methods for large models, encompassing preference-based testing, adversarial attack approaches, issues detection, and other advanced evaluation methods. Additionally, we explore the strategies for enhancing large model safety from training to deployment, highlighting cutting-edge safety approaches for each stage in building large models. Finally, we discuss the core challenges in advancing towards more responsible AI, including the interpretability of safety mechanisms, ongoing safety issues, and robustness against malicious attacks. Through this survey, we aim to provide clear technical guidance for safety researchers and encourage further study on the safety of large models.
SafeRBench: Dissecting the Reasoning Safety of Large Language Models
Nanjing University(南京大学);Fudan University(复旦大学);Carnegie Mellon University(卡内基梅隆大学);Chinese Academy of Sciences(中国科学院);Nanyang Technological University(南洋理工大学)
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)
SaFeR: Safety-Critical Scenario Generation for Autonomous Driving Test via Feasibility-Constrained Token Resampling
School of Traffic and Transportation, Harbin Institute of Technology(哈尔滨工业大学交通学院);Chongqing Research Institute of HIT(哈尔滨工业大学重庆研究所);Chongqing Changan Automobile Company Ltd(重庆长安汽车有限公司)
SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
Department College of Intelligence and Computing(智能与计算学院);Tianjin University(天津大学);NSFOCUS Technologies Group Co., Ltd.(NSFOCUS技术集团有限公司);College of Management and Economics(管理与经济学院);School of Cyber Security(网络安全学院)
Safety Aware Task Planning via Large Language Models in Robotics
University of Minnesota – Twin Cities(明尼苏达大学双城分校);Institute for Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology(佐治亚理工学院机器人与智能机器研究所);Pontificia Universidad Católica de Chile(智利天主教大学)
Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs
Beihang University(北京航空航天大学);Zhongguancun Laboratory(中关村实验室);Hangzhou Innovation Institute, Beihang University(北京航空航天大学杭州创新研究院);Qingdao Research Institute, Beihang University(北京航空航天大学青岛研究院)
HazardAuditor: From Executable Threats to Safer Computer-Use Agents
Ant Group(蚂蚁集团);Zhejiang University(浙江大学);Fudan University(复旦大学);Hunan Institute of Advanced Technology(湖南先进技术研究院);Shanghai Innovation Institute(上海创新研究院);Deakin University(迪肯大学)
LookAhead Tuning: Safer Language Models via Partial Answer Previews
Zhejiang University(浙江大学);Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph(浙江大学-蚂蚁集团知识图谱联合实验室);Ant Group(蚂蚁集团);National University of Singapore(新加坡国立大学)
Retrieval-Guided Generation for Safer Histopathology Image Captioning
Kimia Lab, Department of Artificial Intelligence \& Informatics, Mayo Clinic, Rochester, MN, USA;Department of Biomedical Informatics, University of Arkansas for Medical Sciences, Little Rock, AR, USA;Lane Department of Computer Science;Electrical Engineering, West Virginia University, Morgantown, WV, USA;Department of Computer Science;Engineering, Princeton University, Princeton, NJ, USA;Department of Computer Sciences, University of Wisconsin--Madison, Madison, WI, USA
Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment
Department of Electrical and Computer Engineering(电气与计算机工程系);New Jersey Institute of Technology(新泽西理工学院);Department of Computer Engineering(计算机工程系);Heritage Institute of Technology(遗产理工学院)
Optimal Placement of Roadside Infrastructure Sensors towards Safer Autonomous Vehicle Deployments
Centre of Excellence for Testing & Research of AVs - NTU (CETRAN)(南洋理工大学自动驾驶车辆测试与研究卓越中心(CETRAN));Nanyang Technological University(南洋理工大学);Siemens Mobility Pte. Ltd.(西门子交通私人有限公司)