arXiv AI June 24, 2026 By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud

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

Read the original on arXiv AI →

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

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 AI.

arXiv Machine Learning

Jul 15

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

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.

By Rasmus Torp, Shailen K. Smith, Adam Breuer

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 Machine Learning

Aug 6

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.

By Binyan Xu, Xilin Dai, Di Tang, Kehuan Zhang

llms multimodal safety

arXiv Machine Learning

Jun 24

LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings

arXiv:2602. 18934v2 Announce Type: replace Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning models by revealing whether a specific data point was used during training.

By Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday

benchmarks safety

arXiv Machine Learning

Sep 1

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

arXiv:2608.28934v1 Announce Type: new Abstract: Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In...

By Saloni Modi, Srivi Balaji, Yusong Zhu, Gautam Kamath, Kevin Tian

benchmarks safety

arXiv Machine Learning

Jul 7

GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning

arXiv:2412. 12640v2 Announce Type: replace Abstract: The increasing demand for data privacy, alongside the benefits of aggregating data from networked devices, has catalyzed the emergence of federated learning (FL).

By Rui Zhang, Ka-Ho Chow

llms safety

One email a morning, machine-written

Related stories

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

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

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning