paper-with-me

홈 › Papers

Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks

2025-05-12 · Steffen Schotthöfer, H. Lexie Yang, Stefan Schnake

Deployment of neural networks on resource-constrained devices demands models that are both compact and robust to adversarial inputs. However, compression and adversarial robustness often conflict. In this work, we introduce a dynamical low-rank training scheme enhanced with a novel spectral regularizer that controls the condition number of the low-rank core in each layer. This approach mitigates the sensitivity of compressed models to adversarial perturbations without sacrificing clean accuracy. The method is model- and data-agnostic, computationally efficient, and supports rank adaptivity to automatically compress the network at hand. Extensive experiments across standard architectures, datasets, and adversarial attacks show the regularized networks can achieve over 94% compression while recovering or improving adversarial accuracy relative to uncompressed baselines.

📄 PDF Abstract BibTeX arXiv:2505.08022

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessLow-rank compression

Similar Papers 제목 키워드 기반

Decomposed Trust: Privacy, Adversarial Robustness, Ethics, and Fairness in Low-Rank LLMs

2025-11-27 · Daniel Agyei Asante, Md Mokarram Chowdhury, Yang Li arxiv

Large language models (LLMs) have driven major advances across domains, yet their massive size hinders deployment in resource-constrained settings. Low-rank factorization addresses this challenge by compressing models to…

Adversarial Robustness

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression

2026-01-29 · Xinwei Zhang, Hangcheng Liu, Li Bai, Hao Wang 외 arxiv

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attac…

Adversarial Robustness

On the Effect of Low-Rank Weights on Adversarial Robustness of Neural Networks

2019-01-29 · Peter Langenberg, Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar

Recently, there has been an abundance of works on designing Deep Neural Networks (DNNs) that are robust to adversarial examples. In particular, a central question is which features of DNNs influence adversarial robustnes…

Adversarial Robustness

CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness

2022-12-04 · Huy Phan, Miao Yin, Yang Sui, Bo Yuan 외

Model compression and model defense for deep neural networks (DNNs) have been extensively and individually studied. Considering the co-importance of model compactness and robustness in practical applications, several pri…

Adversarial RobustnessModel Compression

Compression-aware Training of Neural Networks using Frank-Wolfe

2022-05-24 · Max Zimmer, Christoph Spiegel, Sebastian Pokutta

Many existing Neural Network pruning approaches rely on either retraining or inducing a strong bias in order to converge to a sparse solution throughout training. A third paradigm, 'compression-aware' training, aims to o…

Network Pruning