Disha Makhija

4 papers · 2020–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird

Venues

EACL (1) ICML (1) IJCAI (1) NeurIPS (1)

Top co-authors

nhật Hồ (2) Joydeep Ghosh (2) Shreyas Sheshadri (1) Avirup Saha (1) Rashmi Gangadharaiah (1) Niloy Ganguly (1) Xing Han (1) Priyank Patel (1) Samik Datta (1) Manoj Ghuhan Arivazhagan (1)

Research topics

Machine Learning (4) Artificial Intelligence (3) Learning Paradigms · Artificial Intelligence (2) Deep Learning (1) Application Areas (1) Architectures (1) Core AI (1) Core Methods (1) Learning Paradigms · Machine Learning (1) Learning Types (1) Optimization & Theory (1)

Keywords

federated learning (2) differential privacy (1) representation learning (1) semi-supervised learning (1) label propagation (1) model aggregation (1) community detection (1) graph-based learning (1) stochastic block model (1) personalized model (1) privacy auditing (1) bayesian neural network (1) hidden state analysis (1) membership inference attack (1) personalized learning (1) attention pattern (1) heterogeneous architecture (1) neural network (1) heterogeneous setting (1) training data exposure (1)

Papers

Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis EACL 2026 A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings NeurIPS 2024 Architecture Agnostic Federated Learning for Neural Networks ICML 2022 Understanding the Success of Graph-based Semi-Supervised Learning using Partially Labelled Stochastic Block Model IJCAI 2020