paper-with-me

Papers

Applying Tensor Decomposition to image for Robustness against Adversarial Attack

2020-02-28 · Seungju Cho, Tae Joon Jun, Mingu Kang, Daeyoung Kim

Nowadays the deep learning technology is growing faster and shows dramatic performance in computer vision areas. However, it turns out a deep learning based model is highly vulnerable to some small perturbation called an adversarial attack. It can easily fool the deep learning model by adding small perturbations. On the other hand, tensor decomposition method widely uses for compressing the tensor data, including data matrix, image, etc. In this paper, we suggest combining tensor decomposition for defending the model against adversarial example. We verify this idea is simple and effective to resist adversarial attack. In addition, this method rarely degrades the original performance of clean data. We experiment on MNIST, CIFAR10 and ImageNet data and show our method robust on state-of-the-art attack methods.

📄 PDF Abstract BibTeX arXiv:2002.12913

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackDeep LearningTensor Decomposition

Similar Papers 제목 키워드 기반

Bayesian Fully-Connected Tensor Network for Hyperspectral-Multispectral Image Fusion

2025-10-21 · Linsong Shan, Zecan Yang, Laurence T. Yang, Changlong Li 외 arxiv

Tensor decomposition is a powerful tool for data analysis and has been extensively employed in the field of hyperspectral-multispectral image fusion (HMF). Existing tensor decomposition-based fusion methods typically rel…

Bayesian Inference

Robust Tensor Decomposition for Image Representation Based on Generalized Correntropy

2020-05-10 · Miaohua Zhang, Yongsheng Gao, Changming Sun, Michael Blumenstein

Traditional tensor decomposition methods, e.g., two dimensional principal component analysis and two dimensional singular value decomposition, that minimize mean square errors, are sensitive to outliers. To overcome this…

ClusteringFace ReconstructionHandwritten Digit RecognitionImage Clustering+1

Applying Differential Privacy to Tensor Completion

2021-10-01 · Zheng Wei, Zhengpin Li, Xiaojun Mao, Jian Wang

Tensor completion aims at filling the missing or unobserved entries based on partially observed tensors. However, utilization of the observed tensors often raises serious privacy concerns in many practical scenarios. To …

Tensor Decomposition

Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks

2025-09-19 · Het Patel, Muzammil Allie, Qian Zhang, Jia Chen 외 arxiv

Vision language models (VLMs) excel in multimodal understanding but are prone to adversarial attacks. Existing defenses often demand costly retraining or significant architecture changes. We introduce a lightweight defen…

tCURLoRA: Tensor CUR Decomposition Based Low-Rank Parameter Adaptation and Its Application in Medical Image Segmentation

2025-01-04 · Guanghua He, Wangang Cheng, Hancan Zhu, Xiaohao Cai 외

Transfer learning, by leveraging knowledge from pre-trained models, has significantly enhanced the performance of target tasks. However, as deep neural networks scale up, full fine-tuning introduces substantial computati…

Image SegmentationMedical Image Segmentationparameter-efficient fine-tuningSemantic Segmentation+1