Lune

ACL Findings2025

ACCESS DENIED INC: The First Benchmark Environment for Sensitivity Awareness

Dren Fazlija, Arkadij Orlov, Sandipan Sikdar

Abstract

Large language models (LLMs) are increasingly becoming valuable to corporate data management due to their ability to process text from various document formats and facilitate user interactions through natural language queries. However, LLMs must consider the sensitivity of information when communicating with employees, especially given access restrictions.

Simple filtering based on user clearance levels can pose both performance and privacy challenges. To address this, we propose the concept of sensitivity awareness (SA), which enables LLMs to adhere to predefined access rights rules. In addition, we developed a benchmarking environment called ACCESS DENIED INC to evaluate SA. Our experimental findings reveal significant variations in model behavior, particularly in managing unauthorized data requests while effectively addressing legitimate queries. This work establishes a foundation for benchmarking sensitivity-aware language models and provides insights to enhance privacy-centric AI systems in corporate environments. The code and data are available at https://github.com/DrenFazlija/ AccessDeniedInc.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Tree of Attacks: Jailbreaking Black-Box LLMs Automatically cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
  • Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on6

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen et al.ICLR 2024 · 1,104 citations
  3. HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust RefusalMantas Mazeika, Long Phan, Xuwang Yin, Andy Zou et al.ICML 2024 · 1,031 citations
  4. Tree of Attacks: Jailbreaking Black-Box LLMs AutomaticallyAnay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson et al.NeurIPS 2024 · 835 citations
  5. LLM-PBE: Assessing Data Privacy in Large Language ModelsQinbin Li, Junyuan Hong, Chulin Xie, Jeffrey Tan et al.VLDB 2024 · 66 citations

Related papers

  1. Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question AnsweringHwan Chang, Yumin Kim, Yonghyun Jun, Hwanhee LeeEMNLP 2025
  2. DOMBA: Double Model Balancing for Access-Controlled Language Models via Minimum-Bounded AggregationTom Segal, Asaf Shabtai, Yuval EloviciAAAI 2025 · 4 citations
  3. Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone AgentsZhixin Lin, Jungang Li, Shidong Pan, Yibo Shi et al.AAAI 2026 · 7 citations
  4. SecureSQL: Evaluating Data Leakage of Large Language Models as Natural Language Interfaces to DatabasesYanqi Song, Ruiheng Liu, Shu Chen, Qianhao Ren et al.EMNLP Findings 2024 · 6 citations
  5. A Benchmark for Semantic Sensitive Information in LLMs OutputsQingjie Zhang, Han Qiu, Di Wang, Yiming Li et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines