大规模安全：大型模型和智能体安全的全面综述
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
AI总结：
本文综述了大型模型和智能体的安全性，分析了各类攻击威胁及防御策略，指出安全评估、防御机制和数据实践的重要性，强调研究社区和国际合作的必要性。
摘要：
大型模型的快速发展改变了人工智能领域，但其广泛应用也带来了显著的安全风险。本文系统回顾了当前大型模型的安全研究，涵盖视觉基础模型、大型语言模型、视觉-语言预训练模型、视觉-语言模型、扩散模型和智能体。本文总结了安全威胁的分类，包括对抗攻击、数据中毒、后门攻击、劫持和提示注入攻击、能耗-延迟攻击、数据和模型提取攻击以及新兴的智能体特定威胁。我们还回顾了针对每种攻击的防御策略，并总结了常用的数据集和基准。基于此，我们识别并讨论了大型模型安全中的开放挑战，强调了全面的安全评估、可扩展和有效的防御机制以及可持续的数据实践的重要性。更重要的是，我们强调了研究社区和国际合作的必要性。本文为研究人员和实践者提供了有用的参考，促进全面防御系统和平台的持续发展，以保护人工智能模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
