Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging

arXiv:2610.15628 · cs.CV, cs.CR, cs.LG · Submitted 2026-10-11 · Read on arXiv

cs.CV, cs.CR, cs.LG

Submitted: 2026-10-11

Updated: 2026-10-11

Comments: Published in CVPR 2026 Workshops (SAIAD); open access: https://openaccess.thecvf.com/content/CVPR2026W/SAIAD/html/Malatynski_Robust_Detection_of_Directional_Adversarial_Attacks_in_Deep_Neural_Networks_CVPRW_2026_paper.html

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adversarial Attacks — 1× in this paper · explained in 1 episode

Sources

• Explaining and Harnessing Adversarial Examples
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
• Towards Deep Learning Models Resistant to Adversarial Attacks
• A Tutorial on Adversarial Learning Attacks and Countermeasures
• Evaluating Adversarial Robustness: A Comparison Of FGSM, Carlini-Wagner Attacks, And The Role of Distillation as Defense Mechanism
• Intriguing properties of neural networks
• Fast is better than free: Revisiting 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