BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models
cs.CV
Submitted: 2025-11-24
Updated: 2026-09-20
Code: https://github.com/bin015/BackdoorVLM
Terminology
Sources
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Composite Backdoor Attacks Against Large Language Models
- Adam: A Method for Stochastic Optimization
- Qwen2.5-VL Technical Report
- MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- ImgTrojan: Jailbreaking Vision-Language Models with ONE Image
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
- Test-Time Backdoor Attacks on Multimodal Large Language Models
- Backdooring Vision-Language Models with Out-Of-Distribution Data
- Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
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