llm-vulnerability-site

One-page Next.js + Tailwind site for the IEEE ICCIT 2025 paper "Code Poisoning Through Misleading Comments: Jailbreaking Large Language Models via Contextual Deception."

Paper

• Title: Code Poisoning Through Misleading Comments: Jailbreaking Large Language Models via Contextual Deception
• Authors: Aftar Ahmad Sami, Gourob Debnath, Rajon Dey, Abdulla Nasir Chowdhury
• Venue: 2025 28th International Conference on Computer and Information Technology (ICCIT), Cox's Bazar, Bangladesh, 19–21 December 2025
• Pages: 3812–3817
• DOI: 10.1109/ICCIT68739.2025.11491067
• IEEE Xplore: https://ieeexplore.ieee.org/document/11491067
• Dataset (Zenodo): 10.5281/zenodo.15786008

Setup

git clone https://github.com/YOUR_USERNAME/llm-vulnerability-site.git
cd llm-vulnerability-site
npm install
npm run dev

Then open http://localhost:3000.

Citation

@INPROCEEDINGS{11491067,
  author    = {Sami, Aftar Ahmad and Debnath, Gourob and Dey, Rajon and Chowdhury, Abdulla Nasir},
  booktitle = {2025 28th International Conference on Computer and Information Technology (ICCIT)},
  title     = {Code Poisoning Through Misleading Comments: Jailbreaking Large Language Models via Contextual Deception},
  year      = {2025},
  pages     = {3812-3817},
  doi       = {10.1109/ICCIT68739.2025.11491067}
}