arXiv Machine Learning July 15, 2026 By Rasmus Torp, Shailen K. Smith, Adam Breuer

Reducing information dependency does not cause training data privacy. Adversarially non-robust features do

Read the original on arXiv Machine Learning →

arXiv:2607. 12354v1 Announce Type: new Abstract: In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 18

RUB: Evaluating Residual Knowledge in Unlearned Models

arXiv:2504. 14798v2 Announce Type: replace Abstract: Machine Unlearning (MUL) has emerged as a key mechanism for privacy protection and content regulation, yet current techniques often fail to guarantee the complete removal of sensitive information.

By Hao Xuan, Xingyu Li

diffusion benchmarks safety

arXiv AI

3d ago

A Sharp Transition in Data Reconstruction under Differential Privacy

arXiv:2609.37344v1 Announce Type: cross Abstract: Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising privacy concerns and motivat...

By Max Cairney-Leeming, Simone Bombari, Marco Mondelli

safety

arXiv Machine Learning

Jul 16

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training

arXiv:2607. 13541v1 Announce Type: cross Abstract: To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data with text-to-image (T2I)-generated synthetic data, a paradigm we term Real-Synthetic Mix-Training (RSMT).

By Na Li, Boyu Kuang, Hongsheng Hu, Liquan Chen, Hyoungshick Kim, Yansong Gao, Anmin Fu

diffusion safety

arXiv Machine Learning

Jun 2

Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?

arXiv:2409. 01062v4 Announce Type: replace Abstract: Model Inversion (MI) attacks pose a significant privacy threat by reconstructing private training data from machine learning models.

By Viet-Hung Tran, Ngoc-Bao Nguyen, Son T. Mai, Hans Vandierendonck, Ira Assent, Alex Kot, Ngai-Man Cheung

benchmarks safety

arXiv Machine Learning

Jun 17

Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs

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

llms multimodal safety

arXiv AI

Jun 24

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.

By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud

llms benchmarks safety

One email a morning, machine-written

Related stories

RUB: Evaluating Residual Knowledge in Unlearned Models

A Sharp Transition in Data Reconstruction under Differential Privacy

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training

Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?

Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training