Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification
cs.CV, cs.LG
Submitted: 2026-04-16
Updated: 2026-10-13
Terminology
Sources
- HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models
- Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring
- RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computing
- NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learning
- Intriguing properties of neural networks
- Explaining and Harnessing Adversarial Examples
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Adversarial Example in Remote Sensing Image Recognition
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks
- A study of the effect of JPG compression on adversarial images
- Countering Adversarial Images using Input Transformations
- SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models
- HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Experts
- Conflict-Aware Client Selection for Multi-Server Federated Learning
- Federated Mixture-of-Experts Alignment on Mobile Edge Networks under Data Heterogeneity
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models