arXiv Machine Learning September 30, 2026 By Om Shankar Tiwari, Navnit Shukla, Guanyu Wang, Akshay Jain

Privacy-Friendly Cohort Determination: Sealed, CSP-Independent In-Browser ML Inference of Professional Segments for Identity-Less Advertising

Read the original on arXiv Machine Learning →

The Flow has not summarised this story yet — read it at arXiv Machine Learning.

safety

arXiv AI

Sep 1

GuardianAgent: Policy-Conditioned Risk-Adaptive Anonymization with Verified Adversarial Escalation

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

llms agents benchmarks safety

arXiv AI

Aug 26

Ad Insertion in LLM-Generated Responses

arXiv:2601.19435v2 Announce Type: replace-cross Abstract: Sustainable monetization of large language models (LLMs) remains a critical open challenge. Traditional search advertising, which relies on s...

By Shengwei Xu, Zhaohua Chen, Xiaotie Deng, Zhiyi Huang, Grant Schoenebeck

llms safety

arXiv Machine Learning

Jun 18

FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk

arXiv:2502. 17748v4 Announce Type: replace Abstract: Federated Learning (FL) inherently mitigates mass data centralization risks; however, its privacy protections are not equally distributed - leaving vulnerable individuals disproportionately exposed to sophisticated privacy attacks.

By Tianyu Zhao, Mahmoud Srewa, Salma Elmalaki

safety

arXiv Machine Learning

Jun 16

Cross-Silo De-Anonymization Under Local Differential Privacy: Threat Model, Phase Transition, and Coordination Necessity

arXiv:2606. 16763v1 Announce Type: cross Abstract: When a person's records appear in k independent data silos, each protected by (epsilon, delta)-differential privacy, standard composition yields a valid (k*epsilon, k*delta)-DP guarantee for the joint output.

By Ziniu Liu, Aiping Li

safety

Hugging Face Trending Papers

Jun 1

IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning

Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity. In practice, many HDP-FL systems employ $\varepsilon$-aware server aggregation to improve model utility by re-weighting client updates according to their declared privacy budgets.

safety

arXiv AI

Jul 21

Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning

arXiv:2607. 16620v1 Announce Type: cross Abstract: Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems.

By Rakshit Naidu

nlp benchmarks safety

One email a morning, machine-written

Related stories

GuardianAgent: Policy-Conditioned Risk-Adaptive Anonymization with Verified Adversarial Escalation

Ad Insertion in LLM-Generated Responses

FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk

Cross-Silo De-Anonymization Under Local Differential Privacy: Threat Model, Phase Transition, and Coordination Necessity

IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning

Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning