SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of the large language model (LLM) parametric knowledge with non-preferred features is uniformly blocked to all the users. However, this part of knowledge can be useful to advanced users whose expertise qualifies them to handle these information. The one-size-fits-all alignment mechanism undermines LLM's utility for these qualified users. To address this problem, we propose SudoLM, a framework that lets LLMs learn access control over specific parametric knowledge for users with different credentials via authorization alignment. SudoLM allows authorized users to unlock their access to all the parametric knowledge with an assigned SUDO key while blocking access to non-qualified users. Experiments on two application scenarios demonstrate that SudoLM effectively controls the user's access to the parametric knowledge and maintains its general utility.
Code (0)
등록된 구현이 없습니다.
Tasks
AllBlockingLanguage ModelingLanguage ModellingLarge Language ModelSimilar Papers 제목 키워드 기반
A Rule-Based Relational XML Access Control Model in the Presence of Authorization Conflicts
There is considerable amount of sensitive XML data stored in relational databases. It is a challenge to enforce node level fine-grained authorization policies for XML data stored in relational databases which typically s…
Delegated Authorization for Agents Constrained to Semantic Task-to-Scope Matching
Authorizing Large Language Model driven agents to dynamically invoke tools and access protected resources introduces significant risks, since current methods for delegating authorization grant overly broad permissions an…
An Automatic Attribute Based Access Control Policy Extraction from Access Logs
With the rapid advances in computing and information technologies, traditional access control models have become inadequate in terms of capturing fine-grained, and expressive security requirements of newly emerging appli…
AttributeRisk-Aware Fine-Grained Access Control in Cyber-Physical Contexts
Access to resources by users may need to be granted only upon certain conditions and contexts, perhaps particularly in cyber-physical settings. Unfortunately, creating and modifying context-sensitive access control solut…
SoK: Trust-Authorization Mismatch in LLM Agent Interactions
Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP). However, this paradigm shifts control from deterministic code to probabilist…