The paper introduces LLM‑Attacker, a unified framework for evaluating privacy risks in split and distributed large language models. It records attacker choices—such as message types, model weights, datasets, and recovery metrics—to enable consistent comparison and extension of privacy evaluations. Experiments on GPT‑2 show that providing training gradients boosts token recovery from 94.20% to 97.38% and exact‑document recovery from 13.71% to 37.77%, illustrating the framework’s ability to quantify how changes in attacker access affect privacy outcomes.
By Georgios Politis, Evangelos Pappas
Conformal Privacy Auditing (CPA) is a distribution‑free framework that calibrates re‑identification risk for each released document against large language model (LLM)‑empowered adversaries. It outputs a conformal ambiguity set of candidate identities that is guaranteed to contain the true identity with a user‑chosen confidence level under exchangeability, along with an interpretable leakage proxy derived from the set size. CPA supports both logit‑access and sampling‑only attackers, enabling audits of both open‑source and proprietary models, and demonstrates calibrated coverage across various benchmarks and attacker configurations.
By Shuo Huang, Gholamreza Haffari, Xingliang Yuan, Ting Yu, Lizhen Qu
arXiv:2606. 28479v1 Announce Type: cross Abstract: CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy risks under regulations such as GDPR and LGPD.
By Cristhian Kapelinski, Diego Kreutz
arXiv:2606. 17464v1 Announce Type: new Abstract: Membership inference attacks (MIAs) are a canonical way to assess a machine learning model's privacy properties.
By Jeffrey G. Wang, Jason Wang, Marvin Li, Seth Neel
arXiv:2606. 17110v1 Announce Type: cross Abstract: Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets.
By Md Abdullah Al Mamun, Ngoc Phu Doan, Pedram Zaree, Ihsen Alouani, Nael Abu-Ghazaleh
arXiv:2606. 14210v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment.
By Zixuan Gu, Xiaojun Ye, Yang Liu
LLMail-Inject is a large-scale benchmark comprising 208,095 human-written prompt injection attacks gathered from a public red‑teaming challenge with 839 participants. The dataset tests the full attack chain—retrieving prompts from an email database, bypassing production defenses, and triggering unauthorized tool calls with correct arguments. Evaluation shows that models performing well on smaller benchmarks struggle on LLMail-Inject, with GPT‑4o achieving 58% attack success and Meta SecAlign 32%.
By Sahar Abdelnabi, Aideen Fay, Ahmed Salem, Egor Zverev, Kai-Chieh Liao, Chi-Huang Liu, Chun-Chih Kuo, Jannis Weigend, Danyael Manlangit, Alex Apostolov, Haris Umair, Jo\~ao Donato, Masayuki Kawakita, Athar Mahboob, Tran Huu Bach, Tsun-Han Chiang, Myeongjin Cho, Hajin Choi, Byeonghyeon Kim, Hyeonjin Lee, Benjamin Pannell, Conor McCauley, Mark Russinovich, Andrew Paverd, Giovanni Cherubin
arXiv:2601. 07177v5 Announce Type: replace-cross Abstract: Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs).
By Mingxiang Tao, Yu Tian, Wenxuan Tu, Yue Yang, Xue Yang, Xiangyan Tang
arXiv:2606. 00986v1 Announce Type: new Abstract: Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful in privacy sensitive domains such as healthcare and institutional data sharing.
By Ivo Osterberg Nilsson, Maximilian Birr Engvall, Viktor Valadi, Teddy Lazebnik
The paper introduces SparLeak, a side‑channel attack that exploits a new GPU micro‑architectural leakage called Sparsity‑Induced Memory Access (SIMA) caused by sparse attention in large language models. By capturing SIMA traces during LLM inference, SparLeak can infer user‑query attributes from prefill‑phase traces and reconstruct autoregressive responses from decoding‑phase traces. Experiments on three LLM architectures, three sparse attention mechanisms, and three privacy‑sensitive datasets show high success rates (90.9% for attribute inference and 87.3% for response reconstruction), underscoring the need to address SIMA leakage in sparse‑attention deployments.
By Fahao Chen, Linkang Du, Jinhao Zhou, Peng Li, Zhou Su
arXiv:2606. 08372v1 Announce Type: cross Abstract: Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat ("reconstruction", the recovery of an individual's hidden attribute values from a synthetic release and a handful of known quasi-identifiers) has been studied only in scattered, hard-to-compare settings.
By Steven Golob, Sikha Pentyala, Martine De Cock
TextCloak is a reinforcement‑learning driven framework that generates unlearnable examples (UEs) to protect textual data from unauthorized fine‑tuning of large language models (LLMs). It transforms clean text into perturbations that preserve meaning and naturalness while degrading the utility of models trained on them. Experiments on six datasets and nine LLMs show that TextCloak consistently impairs unauthorized fine‑tuning and remains robust across different architectures, training settings, and adaptive attacks.
By Chengshuai Zhao, Pingchuan Ma, Dawei Li, Bohan Jiang, Zhiyuan Yu, Zhen Tan, Huan Liu