Access Control

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 40

All topics

RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation
Sep 27, 2026Yingming Zhou, Adarsh Vatsa, William EiersLarge Language Model Policy Optimization Access Control
Stevens Institute of Technology
Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery
Sep 23, 2026Michael Stettler, Benjamin Girardet, Jonas Canton +1Language-Model Agents Access Control
Skilder
From Alignment to Access Control: A Framework for GenAI Policy Enforcement
Sep 22, 2026Nathalie BaracaldoEnforcement Access Control
IBM Research
Value-Based Massive Access through Goal-Oriented Irregular Repetition Slotted ALOHA
Sep 17, 2026Pietro Talli, Andrea Munari, Federico Mason +2Access Control
Department of Information Engineering, University of Padova, Padua, Italy · Institute of Communications and Navigation, German Aerospace Center (DLR), Weßling, Germany
Empirical Evaluation of Task-Based Permission Scoping Architecture for AI Agents
Sep 14, 2026Halil Burak NoyanAccess Control Kernel-Resident Tool Governance Gateway
Independent Researcher
BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents
Sep 8, 2026Yanhong Qian, Xuanying He, Qingguo Meng +3Kv-Cache Management Key-Value Cache
Anhui Provincial Key Laboratory of Secure Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei 230093, China
Capability-Gated Language Models: Security Composes, Utility Does Not
Aug 31, 2026Patrikas Vanagas, Augustas Mačijauskas, Laurynas LopataLarge Language Model Safety Access Control
BPTI · Independent Researcher · askEarth AG
MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows
Aug 11, 2026Yiqi Wang, Zihao Yan, Jiaqi Zhang +5Graph-Structured Memories Multi-Agent Workflows
Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models
Aug 7, 2026Zhuoheng Huang, Mukesh SinghMixture-Of-Experts Architectures Experts
Independent Researcher
MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication
Aug 3, 2026Jinghan Xu, Longze Fan, Zeyuan Wang +2Disclosures Language-Model Agents
1Nankai University, China · 2China University of Petroleum, China · 3Sun Yat-sen University, China +1
Benchmarking Text-to-SQL under Role-Based Access Control
Jul 24, 2026Yang Fei, Yangfan Jiang, Yin Yang +1Text-To-Sql Access Control
National University of Singapore · Hamad Bin Khalifa University
Eversion-based robots can enable safe access,steering and endoscopic imaging within the spinal subarachnoid space
Jul 21, 2026Zicong Wu, Panagiotis Kalozoumis, S. M. Hadi Sadati +8Robotic Systems Colonoscopy
Department of Surgical & Interventional Engineering, School of Biomedical Engineering & Imaging Sciences, Faculty of Life Sciences & Medicine, King’s College London, London WC2R 2LS, United Kingdom · Department of Computer Science & Biomedical Informatics, University of Thessaly, Lamia 35131, Greece · School of Engineering and Materials Science, Queen Mary University London, London E1 4NS, United Kingdom +2
Policy-Conditioned Constrained Decoding for Column-Level Access Control in Text-to-SQL
Jul 14, 2026Ryoto Miyamoto, Xin Fan, Hayato YamanaText-To-Sql Access Control
Waseda University
Closing the Loop: An Access-Control Architecture for Automated, Anomaly-Driven Network Revocation in IoT Deployments
Jul 13, 2026Muhammet Emir Korkmaz, Kemal Bicakci, Yusuf UzunayInternet Of Thing Logical Anomalies
Securify Information Technology and Security Training Consulting Inc., 06378, Ankara, TÜRK˙IYE · Informatics Institute, Istanbul Technical University, Ayazaga Campus, 34467, Maslak, Istanbul, TÜRK˙IYE
Modular Pretraining Enables Access Control
Jul 9, 2026Ethan Roland, Murat Cubuktepe, Erick Martinez +8Access Control Gating
1AE Studio · 2Independent · 3Anthropic
The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities
Jul 7, 2026Mohammadreza RashidiAccess Control Coding Agents
Department of Computer Science AI and Media Analysis Lab Berlin, Germany
AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis
Jul 4, 2026Adarsh Vatsa, Sachi Shome, Yingming Zhou +1Access Control Large Language Model Policy Optimization
Stevens Institute of Technology
Janus: a Playground for User-Involved Agentic Permission Management
Jul 1, 2026Natalie Grace Brigham, Eugene Bagdasarian, Tadayoshi Kohno +1Access Control Production Agentic Systems
University of Washington · University of Massachusetts Amherst · Georgetown University
Black-Box Inference of LLM Architectural Properties with Restrictive API Access
Jul 1, 2026Christopher Ellis, Shreyas Chaudhari, Mei-Yu Wang +3Attacker Large Language Model Large Language Model Tool Use
Carnegie Mellon University Pittsburgh, PA 15213 · Pittsburgh Supercomputing Center
Dual Agreement Consistency Learning for Semi-Supervised Fetal Ultrasound Segmentation
Jun 24, 2026Fangyijie Wang, Guénolé Silvestre, Ziyang Wang +1High Confidence Pseudo-Labels Semi-Supervised Learning
Research Ireland Centre for Research Training in Machine Learning · School of Medicine, University College Dublin, Dublin, Ireland · School of Computer Science, University College Dublin, Dublin, Ireland +1
Intent-Governed Tool Authorization for AI Agents
Jun 22, 2026Genliang Zhu, Chu WangAuthorization Access Control
Accentrust · Georgia Institute of Technology · University of Illinois Urbana-Champaign
DIPBox: A Multi-scale Testing Framework for Tracking Dataset Regeneration
Jun 19, 2026Tian Dong, Yan Meng, Shaofeng Li +5Adversarial Examples Access Control
Shanghai Jiao Tong University, China · Southeast University, China · Guizhou University, China +1
Policy-aware Vector Search: A Vision for Fine Grained Access Control in Vector Databases
Jun 18, 2026Lakshmi Sahithi Yalamarthi, Primal PappachanVector Database Access Control
Portland State University Portland, Oregon, USA
FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion
Jun 14, 2026Zixin Rao, Wentian Zhu, Chan Aristella Lu +5Attacker Large Language Model Large Language Model Agents
University of Georgia · University of Chicago · University of Illinois Urbana-Champaign
PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry
Jun 9, 2026Gowtham Sivaramakrishnan, Sarvesha Kumar Kombaiah Seetha, Kishan Gupta Balaji +1Large Language Model Adaptation Interference
Independent Researcher
A Training-Efficient Transformer-Based Anti-Spoofing Network for Logical Access in ASVspoof 5
Jun 2, 2026Sidan Yin, Bo ZhaoSpoofing Automatic Speaker Verification
San Domenico School, San Anselmo, CA, United States · University of Washington, Seattle, WA, United States
KISS: Keeping it Simple and Slotted when Learning to Communicate over Wireless
May 29, 2026Kamil Szczech, Maksymilian Wojnar, Krzysztof Rusek +2Decentralized Learning Wifi
AGH University of Krakow, Poland
Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
May 18, 2026Rohith UppalaAccess Control Model Context Protocol
Independent Researcher
Do Coding Agents Understand Least-Privilege Authorization?
May 14, 2026Zheng Yan, Jingxiang Weng, Charles Chen +9Authorization Access Control
Evolvent AI Research Team
Language-Based Agent Control
May 13, 2026Timothy Zhou, Loris D'Antoni, Nadia PolikarpovaAgentic Control Access Control
Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries
May 12, 2026Matthew D. Laws, Alina Oprea, Cristina Nita-RotaruArtificial Intelligence Governance Byzantine Attacks
Northeastern University
Diagnosing and Mitigating Domain Shift in Permission-Based Android Malware Detection
May 9, 2026Md Rafid IslamMitigating Domain Shift Malware
North South University, Department of Electrical and Computer Engineering, Bashundhara, Dhaka, 1229, Bangladesh
Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use
May 6, 2026Francisco Javier Arceo, Varsha Prasad NarsingAccess Control Enterprise Systems
Red Hat AI · Boston, USA
Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI
May 4, 2026Majed El Helou, Benjamin Ryder, Chiara Troiani +3Access Control Agentic Deployments
Cisco Systems, Switzerland
From CRUD to Autonomous Agents: Formal Validation and Zero-Trust Security for Semantic Gateways in AI-Native Enterprise Systems
Apr 28, 2026Ignacio PeyranoAgentic Deployments Semantic Firewall
Universidad Austral Rosario, Argentina
UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks
Apr 25, 2026Tianlong Yu, Yang Yang, Xiao Luo +6Attacker Large Language Model LLM Defense Mechanisms
Hubei University, Wuhan, China · University of Southern California, Los Angeles, USA · Huazhong University of Science and Technology, Wuhan, China
The Open-Weight Paradox: Why Restricting Access to AI Models May Undermine the Safety It Seeks to Protect
Apr 19, 2026Vinicius Santana GomesArtificial Intelligence Governance Governance
Special Advisor, Government of the Federal District of Brazil · AI Instructor, School of Government of the Federal District of Brazil
AgenTRIM: Tool Risk Mitigation for Agentic AI
Jan 18, 2026Roy Betser, Amit Giloni, Shamik Bose +4Agentic Deployments Access Control
Fujitsu Research of Europe (FRE) · Fujitsu Research of India Pvt. Ltd. (FRIPL)
Neurosymbolic Characterization for Reliable Access Control Policy Analysis
Oct 23, 2025Adarsh Vatsa, Bethel Hall, William EiersAccess Control Policy Evaluation
Stevens Institute of Technology
LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach
Oct 13, 2025Renxuan Tan, Rongpeng Li, Fei Wang +4Multi-Agent Reinforcement Learning Stackelberg Equilibrium
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China · Huawei Technologies Company Ltd., Shanghai 210026, China · Zhejiang Lab as well as Zhejiang University, Hangzhou 310027, China +1

Sep 27, 2026, cs.SEJ/K move · Enter open · S save

RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation

Yingming Zhou, Adarsh Vatsa, William Eiers

Stevens Institute of Technology

Large Language Model Policy Optimization Access Control Symbol-

Open paper AskPDF arXiv

Translating natural-language access-control requirements into policies requires careful reasoning about permissions, constraints, and exceptions, and even frontier LLMs often produce policies that violate the intended authorization semantics. We construct CedarInstruct, to our knowledge the first dataset that supports both training and semantic evaluation for formally verifiable Cedar policy synthesis. It contains 5,800 scenarios across 44 domains and 1,408 representing a single synthetic organization, each with a verified target policy and an executable verification plan. On this data we introduce RAISE, which trains policy synthesizers from formal verification in two stages, verified supervised fine-tuning (SFT) followed by a reinforcement learning (RL) stage that learns from verifier signal. We find that SFT succeeds largely by letting models express authorization logic they already have, since untrained models rarely write valid Cedar but often reason correctly when they do. After SFT, how the verifier's information is used matters more than how much of it is used. Of six RL instantiations that consume progressively richer verifier signal, only RAISE-OC improves meaningfully on SFT; it turns failed checks and symbolic counterexamples into guided exploration and learns from the result with off-context GRPO. With about 5.4K verified scenarios and LoRA fine-tuning, RAISE-OC trains Qwen3.5-9B to surpass zero-shot GPT-6 Astra and Claude Opus 5 by 13.33 and 16.26 percentage points in semantic success on held-out scenarios, and training transfers to the independently constructed CedarBench.

Momentum

Related topics

Latest papers 40