Tokenized Key-Gated Adapter Routing (Locket) is a framework that embeds fine‑grained, policy‑driven access control into large language models by training lightweight LoRA adapters for different privacy policies. A gating module associates a learned keyed entry token with a specific adapter, allowing authorized tokens to unlock private knowledge while invalid or missing tokens trigger privacy‑preserving adapters that redact or sanitize sensitive content. Experiments on datasets such as Enron, ECHR, and Yelp with models like Qwen3, Llama‑3.2, and Gemma‑2‑2B show that Locket maintains perplexity comparable to fine‑tuning when the correct token is provided, and significantly reduces PII leakage when the token is absent or invalid, without sacrificing utility.
By Mohamed Shaaban, Mohamed Elmahallawy
arXiv:2607. 22695v1 Announce Type: new Abstract: Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks, leading to widespread deployment.
By Ryan Thornton, Mir Mehedi Ahsan Pritom, Maanak Gupta
The paper introduces Whiteout, a tool that prevents large language models from revealing personally sensitive information (PSI) by overwriting such data with carefully crafted obfuscation samples. Whiteout is evaluated on various LLMs, including an OpenAI model, and shows effective PSI protection with minimal impact on model utility and safety. The study also tests Whiteout against multiple attack vectors and discusses its security and ethical implications.
By Anna Yoo Jeong Ha, Ronik Bhaskar, Haitao Zheng, Ben Y. Zhao
Redakto is a new tool designed to anonymize text before it is processed by large language models (LLMs). It offers state‑of‑the‑art redaction of personally identifiable information (PII) and pseudonymization, accessible via a web interface, REST APIs, and model context protocol hooks. The authors evaluate its performance on legal and medical datasets, showing that anonymized texts retain utility comparable to the originals, enabling LLM tasks without significant loss of effectiveness.
By Saurav Kumar Saha, Tom R\"ohr, Felix Bie{\ss}mann
The paper systematically studies how anonymizing input data affects large language models (LLMs). Five prominent LLMs were evaluated on eleven benchmarks, comparing performance on original versus pseudonymized inputs. Results show that anonymization generally degrades performance, with larger drops for more capable models and task-dependent effects; reversible anonymization preserves entity uniqueness better than irreversible redaction, and prompting about anonymization offers no benefit.
By Tobias Deu{\ss}er, Max Hahnb\"uck, Lorenz Sparrenberg, Tobias Uelwer, Christian Bauckhage, Rafet Sifa
arXiv:2606. 18782v1 Announce Type: cross Abstract: Large Language Models are increasingly applied to sensitive domains that require redaction of personally identifiable information (PII).
By Sean Brynj\'olfsson, Shashvat Jayakrishnan, Esha Sali, Diptanshu Purwar, Madhav Aggarwal
arXiv:2606. 24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges.
By Lorenzo Rossi, Bart{\l}omiej Marek, Franziska Boenisch, Adam Dziedzic
The paper examines how supervised fine-tuning (SFT) of large language models can leak personally identifiable information (PII) when the fine-tuning data contains user-provided sensitive details. It introduces COVA, a coverage-aware decoding algorithm that improves targeted PII reconstruction from SFT models, especially when an adversary has limited contextual knowledge about a target. Experiments on medical and legal Q&A datasets show that even small proprietary SFT datasets can lead to significant privacy leakage via PII reconstruction.
By Sae Furukawa, Alina Oprea
The paper investigates how privacy-preserving sanitization of user context in large language model (LLM) interactions affects downstream performance. It identifies three mechanisms—Context‑Dependent Utility, Strategic Adaptation, and Combinatorial Interplay—that explain when and how to sanitize data. Based on these insights, the authors propose an intent‑driven local protection framework using a lightweight model (Veilmind‑4B) to dynamically extract, sanitize, and restore context, achieving lower privacy leakage while maintaining higher utility than existing baselines.
By Zhenhua Liu, Zhanxu Xie, Junjie Yu, Tong Zhu, Lijun Li, Wenliang Chen
arXiv:2608.29251v1 Announce Type: new
Abstract: Privacy protection for live web traffic requires more than detecting private spans. Agent-based privacy protection systems must determine whether an ou...
By Ruiyi Yang, Gayathri Lihinikaduarachchi, Rahat Masood, Flora D. Salim, Salil S. Kanhere
arXiv:2606. 24623v1 Announce Type: cross Abstract: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts.
By Yuanhe Zhao, Tianyu Zhang, Huafei Xing, Derek F. Wong, Jianbin Li, Tao Fang
arXiv:2310. 16152v5 Announce Type: replace-cross Abstract: Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis.
By Md Rafi Ur Rashid, Vishnu Asutosh Dasu, Kang Gu, Najrin Sultana, Shagufta Mehnaz