GraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural Networks
cs.CV
Submitted: 2026-10-07
Updated: 2026-10-07
Sources
- Detecting Adversarial Samples from Artifacts
- Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples
- A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection
- An Empirical Evaluation of Adversarial Robustness under Transfer Learning
- Adversarial Detection without Model Information
- Representation Learning on Graphs: Methods and Applications
- NeuroTrace: Inference Provenance-Based Detection of Adversarial Examples
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