Copertina

DeepDefense: Layer-Wise Gradient-Feature Alignment for Building Robust Neural Networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lin, Ci, Yeap, Tet, Kiringa, Iluju, Zhang, Biwei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Robust Bidirectional Associative Memory via Regularization Inspired by the Subspace Rotation Algorithm
di: Lin, Ci, et al.
Pubblicazione: (2025)

Preserving Temporal Dynamics in Time Series Generation
di: Lin, Ci, et al.
Pubblicazione: (2026)

Specifying an Obligation Taxonomy in the Non-Markovian Situation Calculus
di: Kalala, Kalonji, et al.
Pubblicazione: (2025)

Relative Layer-Wise Relevance Propagation: a more Robust Neural Networks eXplaination
di: Nyiri, Eric, et al.
Pubblicazione: (2025)

Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients
di: Nguyen, Minh Duong, et al.
Pubblicazione: (2024)

LION-DG: Layer-Informed Initialization with Deep Gradient Protocols for Accelerated Neural Network Training
di: Kim, Hyunjun
Pubblicazione: (2026)

Layer Embedding Deep Fusion Graph Neural Network
di: Xu, Taihua, et al.
Pubblicazione: (2026)

Reconstructing Deep Neural Networks: Unleashing the Optimization Potential of Natural Gradient Descent
di: Liu, Weihua, et al.
Pubblicazione: (2024)

Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers
di: Ye, Donald
Pubblicazione: (2026)

Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense
di: Zhan, Haoxi, et al.
Pubblicazione: (2021)

Energy-Efficient Stochastic Computing (SC) Neural Networks for Internet of Things Devices With Layer-Wise Adjustable Sequence Length (ASL)
di: Wang, Ziheng, et al.
Pubblicazione: (2025)

DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks
di: Gülmez, Gökdeniz
Pubblicazione: (2026)

Certifying Global Robustness for Deep Neural Networks
di: Li, You, et al.
Pubblicazione: (2024)

Deep Multi-View Channel-Wise Spatio-Temporal Network for Traffic Flow Prediction
di: Miao, Hao, et al.
Pubblicazione: (2024)

Symbol Correctness in Deep Neural Networks Containing Symbolic Layers
di: Bembenek, Aaron, et al.
Pubblicazione: (2024)

Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach
di: Mohan, Adithya, et al.
Pubblicazione: (2025)

Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting
di: Hameed, Humza Wajid, et al.
Pubblicazione: (2024)

Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks
di: Dorszewski, Teresa, et al.
Pubblicazione: (2024)

CALM: A CKA-Guided Adaptive Layer-Wise Modularization Framework for LLM Quantization
di: Zhang, Jinhao, et al.
Pubblicazione: (2025)

Imitation Learning Inputting Image Feature to Each Layer of Neural Network
di: Yamane, Koki, et al.
Pubblicazione: (2024)

FAIR-Pruner: A Flexible Framework for Automatic Layer-Wise Pruning via Tolerance of Difference
di: Lin, Chenqing, et al.
Pubblicazione: (2025)

SplitQuant: Layer Splitting for Low-Bit Neural Network Quantization
di: Song, Jaewoo, et al.
Pubblicazione: (2025)

TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training
di: Zhang, Ruijie, et al.
Pubblicazione: (2026)

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
di: Cloud, Alex, et al.
Pubblicazione: (2024)

Axiomatization of Gradient Smoothing in Neural Networks
di: Zhou, Linjiang, et al.
Pubblicazione: (2024)

Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
di: Li, Xin-Chun, et al.
Pubblicazione: (2024)

Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training
di: Ma, Yuhan, et al.
Pubblicazione: (2024)

Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization
di: Wall, Casey, et al.
Pubblicazione: (2025)

Framework GNN-AID: Graph Neural Network Analysis Interpretation and Defense
di: Lukyanov, Kirill, et al.
Pubblicazione: (2025)

Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection
di: Kelodjou, Gwladys, et al.
Pubblicazione: (2023)

FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
di: Liu, Xiang, et al.
Pubblicazione: (2023)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
di: Taniguchi, Rei, et al.
Pubblicazione: (2026)

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
di: Huang, Haoyu, et al.
Pubblicazione: (2026)

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
di: Tang, Xuan, et al.
Pubblicazione: (2025)

Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective
di: Wang, Sifan, et al.
Pubblicazione: (2025)

Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning
di: Wang, Longwei, et al.
Pubblicazione: (2024)

Cross-Entropy Optimization for Hyperparameter Optimization in Stochastic Gradient-based Approaches to Train Deep Neural Networks
di: Li, Kevin, et al.
Pubblicazione: (2024)

Gradient Inversion Attack on Graph Neural Networks
di: Sinha, Divya Anand, et al.
Pubblicazione: (2024)

GradINN: Gradient Informed Neural Network
di: Aglietti, Filippo, et al.
Pubblicazione: (2024)

Gradient-Free Training of Quantized Neural Networks
di: Cohen, Noa, et al.
Pubblicazione: (2024)