让大模型根据用户权限决定是否输出敏感信息
sudoLLM: On Multi-role Alignment of Language Models
- 通过注入用户权限信号，让模型按权限响应
- 显著提升安全对齐与抗越狱攻击能力
- 适合需要权限控制的高安全场景使用
用户授权访问权限是许多安全关键系统的核心功能，但在大语言模型（LLM）领域尚未得到充分研究。本文受访问控制系统启发，提出 sudoLLM 框架，实现多角色对齐的 LLM，即模型能根据用户权限决定行为。该框架在查询中注入细微的用户权限偏置，并训练模型仅当用户授权时才输出敏感信息。实证结果表明，该方法显著提升了对齐性、泛化能力、抗前缀越狱攻击能力以及“失败闭合”特性。语言建模目标与安全对齐之间的固有矛盾——常被用于越狱攻击——在注入偏置信号后得到缓解。该框架作为额外安全层，可与现有防护机制协同，增强大模型端到端的安全性。
原文摘要 · Abstract (English)
User authorization-based access privileges are a key feature in many safety-critical systems, but have not been extensively studied in the large language model (LLM) realm. In this work, drawing inspiration from such access control systems, we introduce sudoLLM, a novel framework that results in multi-role aligned LLMs, i.e., LLMs that account for, and behave in accordance with, user access rights. sudoLLM injects subtle user-based biases into queries and trains an LLM to utilize this bias signal in order to produce sensitive information if and only if the user is authorized. We present empirical results demonstrating that this approach shows substantially improved alignment, generalization, resistance to prefix-based jailbreaking attacks, and ``fails-closed''. The persistent tension between the language modeling objective and safety alignment, which is often exploited to jailbreak LLMs, is somewhat resolved with the aid of the injected bias signal. Our framework is meant as an additional security layer, and complements existing guardrail mechanisms for enhanced end-to-end safety with LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。