---
title: "预测黑盒多轮交互中的轨迹级安全风险"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.26820v1"
permalink: "https://feed.astralor.com/items/itm_a477d1eafaff13f44257558b"
published: "2026-07-29T12:14:23.000Z"
score: 81
channel: "ai"
tags: ["LLM安全","Recast","多轮交互","风险预测"]
---

# 预测黑盒多轮交互中的轨迹级安全风险

## AI 点评

> 这篇论文切中了LLM安全领域的痛点——现有的防护都是事后诸葛亮，而Recast通过轨迹级预测实现了事前预警。对从事AI安全、RLHF和Agent部署的研究者来说，这是值得关注的新范式。实验覆盖率广、指标扎实，尤其是2.41回合的平均提前量让主动干预成为可能。

## 速览

大型语言模型从独立助手进化为自主智能体，其安全风险从单轮评估转向多轮轨迹级预测。本文提出Recast框架，通过双尺度轨迹视角检索短期对话与长期历史证据，建模组合风险演化，并利用因果时序编码器预测未来风险回合分布。实验覆盖7类风险，成功预测88.3%的未来安全故障，平均提前2.41回合预警，误报率12.3%。该工作从被动检测转向主动预防，提升LLM在复杂交互中的安全性。

## 关键点

- 提出Recast框架，将LLM安全从逐轮违禁检测提升至轨迹级风险预测
- 利用双尺度轨迹视角（短期对话+长期历史）检索风险证据
- 因果时序编码器学习潜在风险演化模式，预测未来风险回合分布
- 实验覆盖7类风险，88.3%成功率，平均提前2.41回合，误报率12.3%

## 全文

As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk assessment to understand how risks emerge and unfold over long-horizon trajectories. In multi-turn interactions, malicious intent can be decomposed across seemingly harmless turns and gradually reconstructed through interaction trajectories, eventually resulting in safety failures. Existing safeguards remain largely reactive, detecting manifested violations while lacking the ability to predict latent risk evolution and enable preemptive prevention. To address this limitation, we propose Recast, a safety risk forecasting framework that advances LLM safeguarding beyond turn-level violation detection to trajectory-level risk prediction. Recast first retrieves risk-relevant evidence from both short-term dialogue progression and long-term historical context via a dual-scale trajectory view. It then models compositional risk evolution by capturing the current risk configuration and its temporal dynamics. Finally, a causal temporal encoder learns latent risk evolution patterns and predicts the distribution of future risk emergence turns. Extensive experiments across 7 risk categories show that Recast predicts 88.3% of future safety failures with an average lead time of 2.41 turns, while maintaining a false alarm rate of 12.3%, showcasing the effectiveness of trajectory-level forecasting in identifying emerging risks before safety violations occur.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_a477d1eafaff13f44257558b