Purifying Backdoored Large Vision-Language Models by Removing Hijacked Directions
cs.CV
Submitted: 2026-10-07
Updated: 2026-10-07
Terminology
Sources
- Qwen3-VL Technical Report
- Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- Rethinking the Trigger of Backdoor Attack
- SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
- A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
- Data Poisoning in Deep Learning: A Survey
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