Activation-Space Anchored Access Control for Multi-Class Permission Reasoning in Large Language Models

• URL: http://arxiv.org/abs/2601.13630v1
• Date: Tue, 20 Jan 2026 05:57:44 GMT
• Title: Activation-Space Anchored Access Control for Multi-Class Permission Reasoning in Large Language Models
• Abstract summary: Large language models (LLMs) are increasingly deployed over knowledge bases for efficient knowledge retrieval and question answering.<n>LLMs can inadvertently answer beyond a user's permission scope, leaking sensitive content.<n>We propose Activation-space Anchored Access Control (AAAC), a training-free framework for multi-class permission control.
• Score: 20.49818370567961
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are increasingly deployed over knowledge bases for efficient knowledge retrieval and question answering. However, LLMs can inadvertently answer beyond a user's permission scope, leaking sensitive content, thus making it difficult to deploy knowledge-base QA under fine-grained access control requirements. In this work, we identify a geometric regularity in intermediate activations: for the same query, representations induced by different permission scopes cluster distinctly and are readily separable. Building on this separability, we propose Activation-space Anchored Access Control (AAAC), a training-free framework for multi-class permission control. AAAC constructs an anchor bank, with one permission anchor per class, from a small offline sample set and requires no fine-tuning. At inference time, a multi-anchor steering mechanism redirects each query's activations toward the anchor-defined authorized region associated with the current user, thereby suppressing over-privileged generations by design. Finally, extensive experiments across three LLM families demonstrate that AAAC reduces permission violation rates by up to 86.5% and prompt-based attack success rates by 90.7%, while improving response usability with minor inference overhead compared to baselines.

Related papers

• IFHierBench: Hierarchical Instruction Following for Large Language Models [9.572252219147096]
  We introduce IFHierBench, a hierarchical instruction-following benchmark of 600 prompts stratified across four constraint-tree depths and 35 distinct constraints.<n>We find that even the strongest model only marginally exceeds 50% prompt-level accuracy and that accuracy degrades sharply as constraint depth grows.
  arXiv  Detail & Related papers  (2026-07-30T09:26:06Z)
• Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models [11.113178145712885]
  Large language models (LLMs) are increasingly deployed in enterprise settings where they handle sensitive documents and user context.<n>Conventional access control regulates whether information is accessible to the model, yet leaves how the model uses that information at generation time largely unconstrained.<n>We present Permit, a novel permission-aware representation intervention framework that closes this gap by enforcing fine-grained control directly on the model's hidden states.
  arXiv  Detail & Related papers  (2026-05-10T11:20:48Z)
• Chain-of-Authorization: Internalizing Authorization into Large Language Models via Reasoning Trajectories [21.063230721511726]
  Chain-of-Authorization (CoA) framework internalizes authorization logic into Large Language Models' core capabilities.<n>CoA integrates policy execution with task responses, making authorization a causal prerequisite for substantive responses.
  arXiv  Detail & Related papers  (2026-03-24T07:13:01Z)
• LLMAC: A Global and Explainable Access Control Framework with Large Language Model [0.0]
  Today's business organizations need access control systems that can handle complex, changing security requirements.<n>Current approaches, such as Role-Based Access Control (RBAC), Attribute-Based Access Control (ABAC), and Discretionary Access Control (DAC), were designed for specific purposes.<n>We introduce LLMAC, a new unified approach using Large Language Models (LLMs) to combine these different access control methods into one comprehensive, understandable system.
  arXiv  Detail & Related papers  (2026-02-10T04:02:11Z)
• RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering [62.63376387138257]
  We propose a plug-and-play intervention framework that adaptively steers large language models (LLMs) reasoning in activation space.<n>RISER constructs a library of reusable reasoning vectors and employs a lightweight Router to dynamically compose them for each input.<n>The Router is optimized via reinforcement learning under task-level rewards, activating latent cognitive primitives in an emergent and compositional manner.
  arXiv  Detail & Related papers  (2026-01-14T08:04:33Z)
• MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval [50.30107119622642]
  Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data.<n>Retrieval-Augmented Generation (RAG) addresses this issue by grounding LLMs in external knowledge.<n>MarAG-R1 is a reinforcement-learned multi-tool RAG framework that enables LLMs to dynamically coordinate multiple retrieval mechanisms.
  arXiv  Detail & Related papers  (2025-10-31T15:51:39Z)
• A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA [65.38186593873313]
  Multi-Hop Question Answering (MHQA) requires integrating dispersed, interdependent evidence through sequential reasoning under noise.<n>We introduce a proof-of-concept multi-call framework for MHQA, InfoQA.<n>We construct a stringent and noise-rich benchmark to validate our theory and framework.
  arXiv  Detail & Related papers  (2025-09-25T14:11:57Z)
• MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors [37.488329455418054]
  Large language models (LLMs) enforce safety alignment to reliably refuse malicious requests.<n>But the same blanket safeguards also block legitimate uses in policing, defense, and other high-stakes settings.<n>We introduce Mutually Exclusive Unlock Vectors (MEUV), a lightweight framework that factorizes the monolithic refusal direction into topic-aligned vectors.
  arXiv  Detail & Related papers  (2025-09-04T07:16:06Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router [57.28685457991806]
  DeepSieve is an agentic RAG framework that incorporates information sieving via LLM-as-a-knowledge-router.<n>Our design emphasizes modularity, transparency, and adaptability, leveraging recent advances in agentic system design.
  arXiv  Detail & Related papers  (2025-07-29T17:55:23Z)
• Permissioned LLMs: Enforcing Access Control in Large Language Models [11.090184334137758]
  We propose Permissioned LLMs that superimpose organizational data access control structures on query responses they generate.<n>We empirically evaluate the efficacy of a PermLLM mechanism.<n>We introduce three novel PermLLM mechanisms that build on Efficient Fine-Tuning to achieve the desired access control.
  arXiv  Detail & Related papers  (2025-05-28T20:47:02Z)
• OrgAccess: A Benchmark for Role Based Access Control in Organization Scale LLMs [7.999158988904784]
  Large Language Models (LLMs) serve as unified knowledge repositories and intelligent assistants in enterprise settings.<n> evaluating this crucial capability is inherently difficult due to the proprietary and sensitive nature of real-world corporate data and access control policies.<n>We introduce a synthetic yet representative textbfOrgAccess benchmark consisting of 40 distinct types of permissions commonly relevant across different organizational roles and levels.
  arXiv  Detail & Related papers  (2025-05-25T14:30:15Z)
• Multiple Abstraction Level Retrieve Augment Generation [4.516242893120263]
  A Retrieval-Augmented Generation (RAG) model powered by a large language model (LLM) provides a faster and more cost-effective solution for adapting to new data and knowledge.<n>We propose a novel RAG approach that uses chunks of multiple abstraction levels (MAL), including multi-sentence-level, paragraph-level, section-level, and document-level.<n>Compared to traditional single-level RAG approaches, our approach improves AI evaluated answer correctness of Q/A by 25.739% on Glyco-related papers.
  arXiv  Detail & Related papers  (2025-01-28T13:49:39Z)
• Exploring Language Model Generalization in Low-Resource Extractive QA [57.14068405860034]
  We investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift.<n>We devise a series of experiments to explain the performance gap empirically.
  arXiv  Detail & Related papers  (2024-09-27T05:06:43Z)
• From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification [70.08146540745877]
  We investigate common constraints in NLP tasks, categorize them into three classes based on the types of their arguments. We propose a unified framework, ACT (Aligning to ConsTraints), to automatically produce supervision signals for user alignment with constraints.
  arXiv  Detail & Related papers  (2024-03-10T22:14:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.