DeBUGCN -- Detecting Backdoors in CNNs Using Graph Convolutional Networks
cs.CV, cs.LG
Submitted: 2025-02-25
Updated: 2025-02-25
Terminology
Sources
- Fast Graph Representation Learning with PyTorch Geometric
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
- Spectral Networks and Locally Connected Networks on Graphs
- Deep Residual Learning for Image Recognition
- Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
- Handcrafted Backdoors in Deep Neural Networks
- Densely Connected Convolutional Networks
- The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models
- Semi-Supervised Classification with Graph Convolutional Networks
- Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
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