PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models

Chenyang Zhang, Xiaoyu Zhang, Jian Lou, Kai Wu, Zilong Wang +1 more
2/14/2026

No official code found. Best implementation: 123000001212/PoisonedEye (15 stars, last commit 2025-10-30).

Semantic Scholar

Code Implementations(1)

123000001212/PoisonedEyeCommunity60%

Code of ICML 2025 paper "PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models"

151Python, Jupyter NotebookMay 16, 202511 months ago

Similar Papers

Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions

95% match2026

Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images

94% match1 repo212026

AirDelhi: Fine-Grained Spatio-Temporal Particulate Matter Dataset From Delhi For ML based Modeling

94% match2026

PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation

92% match2026

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

91% match1 repo502026

Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods

91% match1 repo42026

Cite this paper

@article{zhang2026poisonedeye,
  title  = {PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models},
  author = {Chenyang Zhang and Xiaoyu Zhang and Jian Lou and Kai Wu and Zilong Wang and Xiaofeng Chen},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:3ad12c0c4fce3b8b2f58f2d27eae365ad0132415},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/3ad12c0c4fce3b8b2f58f2d27eae365ad0132415.svg)](https://codeofpaper.com/paper/3ad12c0c4fce3b8b2f58f2d27eae365ad0132415)

Discussion