ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus
cs.CV, cs.CR
Submitted: 2026-09-23
Updated: 2026-09-23
Comments: 13 pages, 8 figures (including supplementary materials); Code available at https://github.com/Alex66366/ODPure
Code: https://github.com/Alex66366/ODPure
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Guided Diffusion Model for Adversarial Purification
- Image-to-Video Diffusion: From Foundations to Open Frontiers
- TYPO: Instruction-Dense Visual Jailbreaks against Commercial Closed-Source Image-Generation Models
- Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
- Robot Collapse: Supply Chain Backdoor Attacks Against VLM-based Robotic Manipulation
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
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