Can Attack Difficulty Be Characterized Before Optimization? A Study of Pre-optimization Difficulty in Person-Vanishing Attacks
cs.CV
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- CAT: Customized Adversarial Training for Improved Robustness
- MMA Training: Direct Input Space Margin Maximization through Adversarial Training
- A Safety-Adapted Loss for Pedestrian Detection in Automated Driving
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks
- Identifying Adversarially Attackable and Robust Samples
- Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
- Geometry-aware Instance-reweighted Adversarial Training
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