paper-with-me

홈 › Papers

Evaluating Model Robustness Using Adaptive Sparse L0 Regularization

2024-08-28 · Weiyou Liu, Zhenyang Li, Weitong Chen

Deep Neural Networks have demonstrated remarkable success in various domains but remain susceptible to adversarial examples, which are slightly altered inputs designed to induce misclassification. While adversarial attacks typically optimize under Lp norm constraints, attacks based on the L0 norm, prioritising input sparsity, are less studied due to their complex and non convex nature. These sparse adversarial examples challenge existing defenses by altering a minimal subset of features, potentially uncovering more subtle DNN weaknesses. However, the current L0 norm attack methodologies face a trade off between accuracy and efficiency either precise but computationally intense or expedient but imprecise. This paper proposes a novel, scalable, and effective approach to generate adversarial examples based on the L0 norm, aimed at refining the robustness evaluation of DNNs against such perturbations.

📄 PDF Abstract BibTeX arXiv:2408.15702

Code (0)

등록된 구현이 없습니다.

Tasks

model

Methods 이 논문이 사용한 방법론

NON 설명 없음

Similar Papers 제목 키워드 기반

Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift

2022-10-04 · Yijun Dong, Yuege Xie, Rachel Ward

Concept shift is a prevailing problem in natural tasks like medical image segmentation where samples usually come from different subpopulations with variant correlations between features and labels. One common type of co…

Data AugmentationImage SegmentationMedical Image SegmentationSegmentation+2

Adaptive sparseness for correntropy-based robust regression via automatic relevance determination

2023-01-31 · Yuanhao Li, Badong Chen, Okito Yamashita, Natsue Yoshimura 외

Sparseness and robustness are two important properties for many machine learning scenarios. In the present study, regarding the maximum correntropy criterion (MCC) based robust regression algorithm, we investigate to int…

Bayesian Inferencefeature selectionregression

Adaptive Regularization for Sparsity Control in Bregman-Based Optimizers

2026-05-08 · Ahmad Aloradi, Tim Roith, Emanuël A. P. Habets, Daniel Tenbrinck arxiv

Sparse training reduces the memory and computational costs of deep neural networks. However, sparse optimization methods, e.g., those adding an $\ell_1$ penalty, often control sparsity only indirectly through a regulariz…

Speaker Verification

RAMCT: Novel Region-adaptive Multi-channel Tracker with Iterative Tikhonov Regularization for Thermal Infrared Tracking

2025-04-19 · Shang Zhang, Yuke Hou, Guoqiang Gong, Ruoyan Xiong 외

Correlation filter (CF)-based trackers have gained significant attention for their computational efficiency in thermal infrared (TIR) target tracking. However, ex-isting methods struggle with challenges such as low-resol…

Computational Efficiency

Adaptive and Self-Tuning SBL with Total Variation Priors for Block-Sparse Signal Recovery

2025-03-12 · Hamza Djelouat, Reijo Leinonen, Mikko J. Sillanpää, Bhaskar D. Rao 외

This letter addresses the problem of estimating block sparse signal with unknown group partitions in a multiple measurement vector (MMV) setup. We propose a Bayesian framework by applying an adaptive total variation (TV)…