_version_ 1866914471856832512
author Ma, Xingjun
Gao, Yifeng
Wang, Yixu
Wang, Ruofan
Wang, Xin
Sun, Ye
Ding, Yifan
Xu, Hengyuan
Chen, Yunhao
Zhao, Yunhan
Huang, Hanxun
Li, Yige
Wu, Yutao
Zhang, Jiaming
Zheng, Xiang
Bai, Yang
Wu, Zuxuan
Qiu, Xipeng
Zhang, Jingfeng
Li, Yiming
Han, Xudong
Li, Haonan
Sun, Jun
Wang, Cong
Gu, Jindong
Wu, Baoyuan
Chen, Siheng
Zhang, Tianwei
Liu, Yang
Gong, Mingming
Liu, Tongliang
Pan, Shirui
Xie, Cihang
Pang, Tianyu
Dong, Yinpeng
Jia, Ruoxi
Zhang, Yang
Ma, Shiqing
Zhang, Xiangyu
Gong, Neil
Xiao, Chaowei
Erfani, Sarah
Baldwin, Tim
Li, Bo
Sugiyama, Masashi
Tao, Dacheng
Bailey, James
Jiang, Yu-Gang
author_facet Ma, Xingjun
Gao, Yifeng
Wang, Yixu
Wang, Ruofan
Wang, Xin
Sun, Ye
Ding, Yifan
Xu, Hengyuan
Chen, Yunhao
Zhao, Yunhan
Huang, Hanxun
Li, Yige
Wu, Yutao
Zhang, Jiaming
Zheng, Xiang
Bai, Yang
Wu, Zuxuan
Qiu, Xipeng
Zhang, Jingfeng
Li, Yiming
Han, Xudong
Li, Haonan
Sun, Jun
Wang, Cong
Gu, Jindong
Wu, Baoyuan
Chen, Siheng
Zhang, Tianwei
Liu, Yang
Gong, Mingming
Liu, Tongliang
Pan, Shirui
Xie, Cihang
Pang, Tianyu
Dong, Yinpeng
Jia, Ruoxi
Zhang, Yang
Ma, Shiqing
Zhang, Xiangyu
Gong, Neil
Xiao, Chaowei
Erfani, Sarah
Baldwin, Tim
Li, Bo
Sugiyama, Masashi
Tao, Dacheng
Bailey, James
Jiang, Yu-Gang
contents 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-powered 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_05206
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
Ma, Xingjun
Gao, Yifeng
Wang, Yixu
Wang, Ruofan
Wang, Xin
Sun, Ye
Ding, Yifan
Xu, Hengyuan
Chen, Yunhao
Zhao, Yunhan
Huang, Hanxun
Li, Yige
Wu, Yutao
Zhang, Jiaming
Zheng, Xiang
Bai, Yang
Wu, Zuxuan
Qiu, Xipeng
Zhang, Jingfeng
Li, Yiming
Han, Xudong
Li, Haonan
Sun, Jun
Wang, Cong
Gu, Jindong
Wu, Baoyuan
Chen, Siheng
Zhang, Tianwei
Liu, Yang
Gong, Mingming
Liu, Tongliang
Pan, Shirui
Xie, Cihang
Pang, Tianyu
Dong, Yinpeng
Jia, Ruoxi
Zhang, Yang
Ma, Shiqing
Zhang, Xiangyu
Gong, Neil
Xiao, Chaowei
Erfani, Sarah
Baldwin, Tim
Li, Bo
Sugiyama, Masashi
Tao, Dacheng
Bailey, James
Jiang, Yu-Gang
Cryptography and Security
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
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-powered 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.
title Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
topic Cryptography and Security
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.05206