GPT-5.2、Gemini 3 Pro、Qwen3-VL、Grok 4.1 Fast、Nano Banana Pro 和 Seedream 4.5 的安全报告
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
AI总结：
本报告对六个前沿模型进行综合安全性评估，揭示其在安全性和鲁棒性方面的差异，强调需要标准化评估以指导负责任的部署。
摘要：
大型语言模型（LLMs）和多模态大型语言模型（MLLMs）的快速演变在语言和视觉的推理、感知和生成方面带来了重大进步，但这些进步是否在安全性方面也带来同等的改进仍不清楚，部分原因是评估碎片化，专注于孤立的模态或威胁模型。在本报告中，我们对六个前沿模型——GPT-5.2、Gemini 3 Pro、Qwen3-VL、Grok 4.1 Fast、Nano Banana Pro 和 Seedream 4.5 进行了综合安全性评估，通过统一的协议评估每个模型的语言、视觉-语言和图像生成能力，结合基准测试、对抗测试、多语言泛化和合规性评估。通过将结果汇总到安全排行榜和模型档案中，我们揭示了一个高度不均衡的安全景观：尽管GPT-5.2在基准安全、对抗鲁棒性、多语言泛化和监管合规性方面表现一贯强劲且平衡，其他模型在这些方面存在明显的权衡。尽管在标准基准测试中表现强劲，但所有模型在对抗测试中仍高度脆弱，最坏情况下的安全率降至低于6%。文本到图像模型在受监管的视觉风险类别中表现出略强的对齐性，但在面对对抗性或语义模糊的提示时仍显得脆弱。总体而言，这些发现表明，前沿模型的安全性本质上是多维的——由模态、语言和评估设计塑造，强调了需要标准化、全面的安全评估以更好地反映现实世界的风险并指导负责任的部署。
英文摘要：
The rapid evolution of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has driven major gains in reasoning, perception, and generation across language and vision, yet whether these advances translate into comparable improvements in safety remains unclear, partly due to fragmented evaluations that focus on isolated modalities or threat models. In this report, we present an integrated safety evaluation of six frontier models--GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5--assessing each across language, vision-language, and image generation using a unified protocol that combines benchmark, adversarial, multilingual, and compliance evaluations. By aggregating results into safety leaderboards and model profiles, we reveal a highly uneven safety landscape: while GPT-5.2 demonstrates consistently strong and balanced performance, other models exhibit clear trade-offs across benchmark safety, adversarial robustness, multilingual generalization, and regulatory compliance. Despite strong results under standard benchmarks, all models remain highly vulnerable under adversarial testing, with worst-case safety rates dropping below 6%. Text-to-image models show slightly stronger alignment in regulated visual risk categories, yet remain fragile when faced with adversarial or semantically ambiguous prompts. Overall, these findings highlight that safety in frontier models is inherently multidimensional--shaped by modality, language, and evaluation design--underscoring the need for standardized, holistic safety assessments to better reflect real-world risk and guide responsible deployment.
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。
