Projects & research.

developed a machine-learning framework for detecting and mitigating data-poisoning attacks.

• Shray Gupta — profile project record →

Java/Spring Boot prototype for food-product APIs, QR-code generation and basic payment-transaction records, using configurable H2/MySQL storage.

• Mohammad Aakil — profile project record →

a Python/Ollama prototype that checks syntax, generates code corrections and retries following execution errors.

• Shaili Bansal — profile project record →

a policy-document question-answering prototype combining risk detection, adaptive retrieval, answer evaluation, evidence checks and retrieval repair.

• Shaili Bansal — profile project record →

the published study investigates inference-time backdoor-sample detection through internal stability analysis.

• Mahaveer Prasad — profile project record →

React and Material UI interview-management prototype with interview creation, expert listings, search and a skill-discussion interface.

• Ayush Kumar — profile project record →

Primary developer of Towerdefense, a Mindustry server plugin with configurable waves, shops, an in-game economy and gameplay-tuning systems.

• Ayush Kumar — profile project record →

Python and FastAPI project for PDF extraction, Gemini-assisted translation and layout reconstruction, with command-line and web interfaces.

• Ayush Kumar — profile project record →

contributed to a Q-learning-based routing system for underwater software-defined networks.

• Ishan Panwar — profile project record →

public FastAPI training and prediction pipeline with MongoDB ingestion, S3 model storage and Docker packaging.

• Ajit Kumar Yadav — profile project record →

developed a CNN/OCR pipeline in Python using OpenCV, imutils and Tesseract for traffic-monitoring images.

• Ganesh Immanni — profile project record →

Built encrypted-traffic and VPN research software for collection coordination, traffic preparation, feature extraction, model training, evaluation and experiment provenance, using third-party tools and libraries. The work includes traffic contributed by Ayush Kumar and volunteers during everyday device use, kept distinct from imported benchmarks and synthetic examples. The study has documented consent and institutional ethics approval. Its public Android companion uses the PCAPdroid capture engine. A truncated public data edition is prepared locally and awaits publication; raw research access for trusted researchers and organisations is considered through enquiry and review.

• Ayush Kumar — profile project record →