Aditya Yadav

• Developed a deepfake detection system using CNN-based binary classifier on FaceForensics++ dataset.
• Achieved 93% accuracy distinguishing real vs AI-generated images.
• Reduced false-negative rate by 18% over VGG16 baseline via augmentation and domain fine-tuning.

• Built and evaluated a salary prediction model using CNN and GAN on IBM Adult3 dataset (100K+ records).
• Achieved 87% classification accuracy — 11% above logistic regression baseline.
• Model shortlisted for internal HR analytics review after presentation of feature importance findings.

Privacy-first mobile chat app built for a national security hackathon. Passed adversarial red-team evaluation with zero data-leak findings.

• End-to-end encryption via Libsodium, ephemeral TTL messaging
• Serverless P2P architecture — no central server
• Zero data-leak findings in adversarial red-team evaluation

Full-stack web app centralizing internships, research, and hackathons for students. 200+ users onboarded in first month.

• 200+ students onboarded within first month of launch
• Advanced search, filtering, bookmarking, and user dashboards
• Reduced opportunity-discovery time by ~60% vs manual search

Biomedical RAG pipeline using Bio-Mistral LLM with vector database retrieval for context-aware medical responses.

• Biomedical text embeddings stored and queried from vector DB
• Semantic retrieval + context-aware, human-like response generation
• Built as part of Guvi certification project