AprielGuard：一个统一安全与对抗防御的8B参数模型
AprielGuard
AI总结：
AprielGuard是一个统一安全与对抗防御的8B参数模型，通过多任务训练在多步骤和推理场景中有效检测有害内容和对抗操纵。
摘要：
保护大型语言模型（LLMs）以防止不安全或对抗性行为至关重要，因为它们越来越多地部署在对话和代理设置中。现有的审核工具往往将安全风险（例如毒性、偏见）和对抗性威胁（例如提示注入、 jailbreaks）视为单独的问题，限制了其鲁棒性和通用性。我们介绍了AprielGuard，一个8B参数保护模型，它在一个单一的分类法和学习框架内统一了这些维度。AprielGuard是在涵盖独立提示、多轮对话和代理工作流程的多样化开放和合成数据上训练的，辅以结构化推理轨迹以提高可解释性。在多个公共和专有基准测试中，AprielGuard在检测有害内容和对抗性操纵方面表现出色，优于现有的开源防护措施，如Llama-Guard和Granite Guardian，特别是在多步骤和推理密集型场景中。通过发布该模型，我们旨在推动关于LLM可靠防护措施的透明和可重复研究。
英文摘要：
Safeguarding large language models (LLMs) against unsafe or adversarial behavior is critical as they are increasingly deployed in conversational and agentic settings. Existing moderation tools often treat safety risks (e.g. toxicity, bias) and adversarial threats (e.g. prompt injections, jailbreaks) as separate problems, limiting their robustness and generalizability. We introduce AprielGuard, an 8B parameter safeguard model that unify these dimensions within a single taxonomy and learning framework. AprielGuard is trained on a diverse mix of open and synthetic data covering standalone prompts, multi-turn conversations, and agentic workflows, augmented with structured reasoning traces to improve interpretability. Across multiple public and proprietary benchmarks, AprielGuard achieves strong performance in detecting harmful content and adversarial manipulations, outperforming existing opensource guardrails such as Llama-Guard and Granite Guardian, particularly in multi-step and reasoning intensive scenarios. By releasing the model, we aim to advance transparent and reproducible research on reliable safeguards for LLMs.
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。
