arXiv Machine Learning June 3, 2026 By Prashant Shekhar, Caroline Howard

Privacy-Robust Incrementality Measurement for Advertising Systems under Signal Loss

Read the original on arXiv Machine Learning →

arXiv:2606. 03878v1 Announce Type: cross Abstract: Advertising platforms use randomized lift tests to measure incrementality, but privacy-preserving reporting systems degrade the observed signal through match-rate loss, linkability loss, attribution-window loss, aggregation-threshold suppression, randomized reporting noise, and segment-heterogeneous signal loss.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv AI

Jun 11

Robust Privacy: Inference-Stage Privacy through Certified Robustness

arXiv:2601. 17360v2 Announce Type: replace-cross Abstract: An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives of the model's training data.

By Jiankai Jin, Xiangzheng Zhang, Zhao Liu, Wenzhuo Xu, Dongdong Yang, Deyue Zhang, Quanchen Zou

efficiency multimodal safety

arXiv AI

Jun 17

Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning

arXiv:2503. 10945v3 Announce Type: replace-cross Abstract: Current practices for reporting differential privacy (DP) guarantees for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture.

By Juan Felipe Gomez, Bogdan Kulynych, Georgios Kaissis, Flavio P. Calmon, Jamie Hayes, Borja Balle, Antti Honkela

computer-vision benchmarks safety

arXiv Machine Learning

22h ago

Picture the Epsilon: Pursuing Identity-Level Privacy Guarantees for Images

arXiv:2608. 17147v1 Announce Type: cross Abstract: Image-to-image face generators are widely used, and visual dissimilarity between their outputs and source images is sometimes treated as evidence of privacy.

By Arman Zareian Jahromi, Vishnu Bondalakunta, Mohammad Akbar Bin Shah, Naimul Haque, Shuangqing Wei, George T. Amariucai

rag safety

arXiv AI

Jun 2

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

arXiv:2606. 00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users.

By Mingxuan Zhang, Jiahui Han, Dadi Guo, Songze Li, Guanchu Wang, Na Zou, Dongrui Liu, Xia Hu

llms agents benchmarks safety

arXiv Machine Learning

Jul 7

Efficient privacy loss accounting for subsampling and random allocation

arXiv:2602. 17284v2 Announce Type: replace Abstract: We consider the privacy amplification properties of a sampling scheme in which a user's data isused in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps.

By Vitaly Feldman, Moshe Shenfeld

safety

arXiv Machine Learning

Jun 4

Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD

arXiv:2606. 04384v1 Announce Type: new Abstract: Machine learning's reliance on sensitive data necessitates privacy-preserving techniques like Differentially Private Stochastic Gradient Descent (DPSGD).

By Xiaobo Huang, Fang Xie

safety

Related stories

Robust Privacy: Inference-Stage Privacy through Certified Robustness

Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning

Picture the Epsilon: Pursuing Identity-Level Privacy Guarantees for Images

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

Efficient privacy loss accounting for subsampling and random allocation

Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD