Results 101 to 110 of about 25,829 (292)

Defense Architecture for Adversarial Examples of Ensemble Model Traffic Based on FeatureDifference Selection [PDF]

Jisuanji kexue
Currently,anomaly traffic detection models that leverage deep learning technologies are increasingly vulnerable to adversarial example attacks.Adversarial training has emerged as a potent defense mechanism against these adversarial attacks.By ...
HE Yuankang, MA Hailong, HU Tao, JIANG Yiming
doaj   +1 more source

SpaMode: A Broadly Applicable Framework for Deciphering Spatial Multi‐Omics Using Multimodal Mixture of Disentangled Experts

Advanced Science, EarlyView.
SpaMode introduces a versatile framework for spatial multi‐omics integration across vertical, horizontal, and mosaic scenarios. By disentangling modality‐invariant and variant features through a mixture‐of‐experts mechanism, it adaptively reconfigures spatially heterogeneous signals.
Xubin Zheng, Xinlei Huang, Xiang Zhou, Dian Meng, Ziyue Qiao, Zhiyuan Yuan, Lixin Cheng   +6 more
wiley   +1 more source

MTFM: Multi-Teacher Feature Matching for Cross-Dataset and Cross-Architecture Adversarial Robustness Transfer in Remote Sensing Applications

Remote Sensing
Remote sensing plays a critical role in environmental monitoring, land use analysis, and disaster response by enabling large-scale, data-driven observation of Earth’s surface.
Ravi Kumar Rogannagari, Kazi Aminul Islam   +1 more
doaj   +1 more source

DERD: Data-free Adversarial Robustness Distillation through Self-adversarial Teacher Group

Computer vision models based on deep neural networks are proven to be vulnerable to adversarial attacks. Robustness distillation, as a countermeasure, takes both robustness challenges and efficiency challenges of edge models into consideration.
Zhou, Yuhang, Hua, Zhongyun, Zhang, Leo Yu, Zhang, Yushu   +3 more
core   +1 more source

Diffusion‐Based Generative Model With Scaffold‐Hopping Strategy Yields Highly Potent Bioactive Molecules

Advanced Science, EarlyView.
SMarT‐Diff introduces a multi‐objective generative paradigm that integrates scaffold hopping with structure‐aware scoring to enable controlled exploration beyond the training distribution. The framework consistently balances drug‐likeness, synthesizes accessibility and bioactivity, yielding chemically diverse candidates with enhanced properties.
Yuwei Yang, Xiaoqing Gong, Shukai Gu, Jing Li, Bo Liu, Yanan Tian, Qianqian Zhang, Xiaojun Yao, Huanxiang Liu   +8 more
wiley   +1 more source

Regularization for Adversarial Robust Learning

CoRR
51 pages, 5 ...
Jie Wang, Rui Gao, Yao Xie
openaire   +2 more sources

Provably Robust Adversarial Examples

, 2020
International Conference on Learning Representations (ICLR 2022)
Dimitar Iliev Dimitrov, Gagandeep Singh 0001, Timon Gehr, Martin T. Vechev   +3 more
openaire   +4 more sources

Rethinking data augmentation for adversarial robustness [PDF]

Recent work has proposed novel data augmentation methods to improve the adversarial robustness of deep neural networks. In this paper, we re-evaluate such methods through the lens of different metrics that characterize the augmented manifold, finding ...
Eghbal-zadeh, Hamid, Koutini, Khaled, Biggio, Battista, Zellinger, Werner, Moser, Bernhard A., Widmer, Gerhard, Pintor, Maura, Grosse, Kathrin   +7 more
core   +1 more source

Adversarial robustness for unsupervised domain adaptation

, 2021
Extensive Unsupervised Domain Adaptation (UDA) studies have shown great success in practice by learning transferable representations across a labeled source domain and an unlabeled target domain with deep models.
ZHOU, F, Hong, L, Luo, P, LI, Z, Xu, H, Bae, SH, AWAIS, W   +6 more
core   +1 more source

From Label‐Free Multiphoton Imaging to Pathological Reports: A Vision‐Language Breast Cancer Margin Pathological Diagnosis System

Advanced Science, EarlyView.
MarginPath is a novel vision‐language system that automates breast cancer margin assessment using a single label‐free multiphoton microscopy image. By integrating tumor‐associated collagen signatures with virtual H&E imaging, it generates accurate margin heatmaps and comprehensive diagnostic reports.
Shu Wang, Jingze Su, Xiahui Han, Deyong Kang, Xiao Zhang, Fei Xu, Changzu Liu, Junlin Pan, Xingfu Wang, Qiaohui Zhan, Aimin Wang, Feng Huang, Heping Cheng, Wenxi Liu, Ruolan Lin, Jianxin Chen   +15 more
wiley   +1 more source