paper-with-me

홈 › Papers

Boosting Adversarial Robustness and Generalization with Structural Prior

2025-02-02 · Zhichao Hou, Weizhi Gao, Hamid Krim, Xiaorui Liu

This work investigates a novel approach to boost adversarial robustness and generalization by incorporating structural prior into the design of deep learning models. Specifically, our study surprisingly reveals that existing dictionary learning-inspired convolutional neural networks (CNNs) provide a false sense of security against adversarial attacks. To address this, we propose Elastic Dictionary Learning Networks (EDLNets), a novel ResNet architecture that significantly enhances adversarial robustness and generalization. This novel and effective approach is supported by a theoretical robustness analysis using influence functions. Moreover, extensive and reliable experiments demonstrate consistent and significant performance improvement on open robustness leaderboards such as RobustBench, surpassing state-of-the-art baselines. To the best of our knowledge, this is the first work to discover and validate that structural prior can reliably enhance deep learning robustness under strong adaptive attacks, unveiling a promising direction for future research.

📄 PDF Abstract BibTeX arXiv:2502.00834

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessDeep LearningDictionary Learning

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Pyramid Adversarial Training Improves ViT Performance

2021-11-30 · CVPR 2022 1 · Charles Herrmann, Kyle Sargent, Lu Jiang, Ramin Zabih 외

Aggressive data augmentation is a key component of the strong generalization capabilities of Vision Transformer (ViT). One such data augmentation technique is adversarial training (AT); however, many prior works have sho…

Adversarial AttackData AugmentationDomain GeneralizationImage Classification

Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticity

2026-05-02 · Joy Dhar, Song Xia, Manish Kumar Pandey, Maryam Haghighat 외 arxiv

We introduce Hybrid Convolutions with Attention Stochasticity (HyCAS), an adversarial defense that narrows the long-standing gap between provable robustness under L2 certificates and empirical robustness against strong L…

Adversarial RobustnessAdversarial Defense

A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness

2021-03-01 · Jacob Abernethy, Pranjal Awasthi, Satyen Kale

Alongside the well-publicized accomplishments of deep neural networks there has emerged an apparent bug in their success on tasks such as object recognition: with deep models trained using vanilla methods, input images c…

Adversarial RobustnessObject Recognition

Randomized Adversarial Training via Taylor Expansion

2023-03-19 · CVPR 2023 1 · Gaojie Jin, Xinping Yi, Dengyu Wu, Ronghui Mu 외

In recent years, there has been an explosion of research into developing more robust deep neural networks against adversarial examples. Adversarial training appears as one of the most successful methods. To deal with bot…

Spectral regularization for adversarially-robust representation learning

2024-05-27 · Sheng Yang, Jacob A. Zavatone-Veth, Cengiz Pehlevan

The vulnerability of neural network classifiers to adversarial attacks is a major obstacle to their deployment in safety-critical applications. Regularization of network parameters during training can be used to improve …

Adversarial RobustnessRepresentation LearningSelf-Supervised Learning