Skip to content
View Atishay17's full-sized avatar

Highlights

  • Pro

Block or report Atishay17

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Atishay17/README.md

Hi, I'm Atishay 👋

CS graduate (BVCOE, GGSIPU) working at the intersection of ML security, computer vision, and applied research. Ex-research intern at DRDO DIT-CS, currently applying for MS in CS/AI/ML.

I like building things that turn into papers, not just demos.


🔬 Currently

  • Finishing revisions on two research papers (vulnerability detection + phishing detection)
  • Applying for MS programs in Germany (TUM, TU Berlin)
  • Open to research internships / research-adjacent roles in the meantime

📌 Featured work

Project What it does Result
graphcodebert-cwe-detection Multi-label vulnerability detection (CWE-89/362/639) using GraphCodeBERT Macro F1: 0.9049
visual-phishing-detection Phishing detection by rendering pages as screenshots + ResNet-18 AUC-ROC: 0.9548
Clinical-Foot-Ulcer-Segmentation Foot ulcer image segmentation using multiple U-Net architectures Medical imaging / wound delineation

🛠️ Stack

Python · PyTorch · Transformers (GraphCodeBERT, CodeBERT) · CNNs (ResNet, EfficientNet, U-Net) · Scikit-learn · OpenCV


📫 Reach me: LinkedIn · Email GitHub Stats

Pinned Loading

  1. Clinical-Foot-Ulcer-Segmentation Clinical-Foot-Ulcer-Segmentation Public

    Deep learning-based clinical foot ulcer image segmentation using multiple U-Net architectures for accurate wound delineation.

  2. graphcodebert-cwe-detection graphcodebert-cwe-detection Public

    Multi-label vulnerability detection for CWE-89/362/639 using GraphCodeBERT. Macro F1: 0.9049. Paper under review.

  3. visual-phishing-detection visual-phishing-detection Public

    Phishing detection via webpage screenshots + ResNet-18. AUC-ROC: 0.9548. Paper under revision @ PES.