arXiv AI July 3, 2026 By R\'ois\'in Luo, James McDermott, Colm O'Riordan

Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition

arXiv:2408. 01139v4 Announce Type: replace Abstract: Perturbation robustness evaluates the vulnerabilities of models, arising from a variety of perturbations, such as data corruptions and adversarial 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 AI.

arXiv Machine Learning

Jun 4

Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms

arXiv:2606. 04767v1 Announce Type: new Abstract: The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack interpretability.

By Chong Zhang, Xiang Li, Jia Wang, Qiufeng Wang, Xiaobo Jin

llms safety

arXiv Computer Vision

Sep 15

Sparsity-Adaptive Sharpness-Aware Minimization

The paper introduces Sparsity-Adaptive Sharpness-Aware Minimization (SA‑SAM), a method that adjusts the perturbation radius in sharpness-aware training to remain consistent as model sparsity increases. It also evaluates a Magnitude‑Weighted Hessian (MWH) importance metric derived from second‑order analysis. Experiments on CIFAR‑10‑C, CIFAR‑100‑C, and ImageNet‑100‑C show that SA‑SAM improves corruption robustness at 80–90% sparsity while maintaining clean accuracy, and the study reports inference throughput at deployment‑relevant sparsity levels.

By Shiryu Ueno, Yoshikazu Hayashi, Kunihito Kato

efficiency

arXiv AI

Jun 16

Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability

arXiv:2606. 16883v1 Announce Type: cross Abstract: Generalization is a critical property of data-driven models, particularly deep learning models deployed in safety-critical applications.

By Abdul-Rauf Nuhu, Parham M. Kebria, Vahid Hemmati, Mahmoud N. Mahmoud, Edward Tunstel, Abdollah Homaifar

safety

arXiv Computer Vision

Sep 22

Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models

arXiv:2609.22293v1 Announce Type: new Abstract: Vision-language models (VLMs) and vision-language-action models (VLAs) are increasingly deployed in real-world applications. There, a small perturbatio...

By Bogdan Aron, Christopher Brix, Benedikt Br\"uckner, Yanghao Zhang, Panagiotis Kouvaros, Alessio Lomuscio

llms multimodal benchmarks

arXiv Machine Learning

Jun 25

Robust Linear Predictions: Analyses of Uniform Concentration, Fast Rates and Model Misspecification

arXiv:2201. 01973v3 Announce Type: replace-cross Abstract: The problem of linear predictions has been extensively studied for the past century under pretty generalized frameworks.

By Saptarshi Chakraborty, Debolina Paul, Swagatam Das

arXiv AI

Jun 9

A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers

arXiv:2606. 07593v1 Announce Type: cross Abstract: The widespread use of image classification models in high-risk, real-world situations necessitates making these models robust to slight disturbances or perturbations, such as blurring or sharpening, in the input images.

By Hannah Gao (Massachusetts Institute of Technology), Isha Agarwal (Massachusetts Institute of Technology), Dylan Hadfield-Menell (Massachusetts Institute of Technology), Rachel Ma (Massachusetts Institute of Technology)

llms computer-vision fine-tuning multimodal safety