Safety at Scale: A Comprehensive Survey of Large Model Safety

Abstract—The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a wide range of applications, including conversational AI, recommendation systems, autonomous driving, content generation, medical diagnostics, and scientific discovery. However, their widespread deployment also exposes them to significant safety risks, raising concerns about robustness, reliability, and ethical implications. This survey provides a systematic review of current safety research on large models, covering Vision Foundation Models (VFMs), Large Language Models (LLMs), Vision-Language Pre-training (VLP) models, Vision-Language Models (VLMs), Diffusion Models (DMs), and large-model-based Agents. Our contributions are summarized as follows: (1) We present a comprehensive taxonomy of safety threats to these models, including adversarial attacks, data poisoning, backdoor attacks, jailbreak and prompt injection attacks, energy-latency attacks, data and model extraction attacks, and emerging agent-specific threats. (2) We review defense strategies proposed for each type of attacks if available and summarize the commonly used datasets and benchmarks for safety research. (3) Building on this, we identify and discuss the open challenges in large model safety, emphasizing the need for comprehensive safety evaluations, scalable and effective defense mechanisms, and sustainable data practices. More importantly, we highlight the necessity of collective efforts from the research community and international collaboration. Our work can serve as a useful reference for researchers and practitioners, fostering the ongoing development of comprehensive defense systems and platforms to safeguard AI models. GitHub: https://github.com/xingjunm/Awesome-Large-Model-Safety. Index Terms—Large Model Safety, AI Safety, Attacks and Defenses

Authors

Publication Details

Journal
SuperIntelligence - Robotics - Safety & Alignment
Published
2025-05-29
DOI
https://doi.org/10.70777/si.v2i2.14609
Primary Topic
Occupational Health and Safety Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Safety at Scale: A Comprehensive Survey of Large Model Safety

Chaowei Xiao, Neil Zhenqiang Gong, Yifan Ding, Cihang Xie et al.
1 links
SuperIntelligence - Robotics - Safety & Alignment
Occupational Health and Safety Research
article

Safety at Scale: A Comprehensive Survey of Large Model Safety

Chaowei Xiao, Neil Zhenqiang Gong, Yifan Ding, Cihang Xie, Shiqing Ma, Tianyu Pang, Ruoxi Jia, Yixu Wang, Xipeng Qiu, Yunhao Chen, Yu–Gang Jiang, Hanxun Huang, Jindong Gu, Hengyuan Xu, Xiang Zheng, Tongliang Liu, Siheng Chen, Baoyuan Wu, Yinpeng Dong, Sarah Erfani, Masashi Sugiyama, Dacheng Tao, Yige Li, Xingjun Ma, Xiangyu Zhang, Bo Li, Cong Wang, Jiaming Zhang, Ye Sun, Ruofan Wang, Yang Liu, Jun Sun, Jingfeng Zhang, Yang Bai, Yunhan Zhao, Shirui Pan, Yang Zhang, Tianwei Zhang, James Bailey, Mingming Gong, Xin Wang, Yifeng Gao, Yiming Yi
article en

Abstract

Abstract—The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a wide range of applications, including conversational AI, recommendation systems, autonomous driving, content generation, medical diagnostics, and scientific discovery. However, their widespread deployment also exposes them to significant safety risks, raising concerns about robustness, reliability, and ethical implications. This survey provides a systematic review of current safety research on large models, covering Vision Foundation Models (VFMs), Large Language Models (LLMs), Vision-Language Pre-training (VLP) models, Vision-Language Models (VLMs), Diffusion Models (DMs), and large-model-based Agents. Our contributions are summarized as follows: (1) We present a comprehensive taxonomy of safety threats to these models, including adversarial attacks, data poisoning, backdoor attacks, jailbreak and prompt injection attacks, energy-latency attacks, data and model extraction attacks, and emerging agent-specific threats. (2) We review defense strategies proposed for each type of attacks if available and summarize the commonly used datasets and benchmarks for safety research. (3) Building on this, we identify and discuss the open challenges in large model safety, emphasizing the need for comprehensive safety evaluations, scalable and effective defense mechanisms, and sustainable data practices. More importantly, we highlight the necessity of collective efforts from the research community and international collaboration. Our work can serve as a useful reference for researchers and practitioners, fostering the ongoing development of comprehensive defense systems and platforms to safeguard AI models. GitHub: https://github.com/xingjunm/Awesome-Large-Model-Safety. Index Terms—Large Model Safety, AI Safety, Attacks and Defenses

SuperIntelligence - Robotics - Safety & AlignmentVol. 2(2)
Openalex Percentile: Top 83%
Occupational Health and Safety Research
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.