Research programme

Projects & research.

Research studies, software and prototypes from across the NPerseus team.

Projects across the team

Research studies, prototypes and software described in public profiles. Status, roles and funding follow each source record; a profile entry does not by itself establish a released product.

Thesis topics, funded studies and method work: attacks, defenses, data hiding, forensics and the datasets behind them.

32 matching research project records · Page 2 of 3

Member project Research

Android Malware Characterization research

Mahaveer Prasad

the published study classifies Android malware using high-level behavioral features.

Link to this project
Member project Research

Backdoor Attacks and Detection in Data Distillation (ongoing)

Priyanshu Yadav

investigates vulnerabilities in distilled datasets and develops poisoned-sample detection methods using feature-space analysis, layer-wise representation consistency, Mahalanobis distance and feature similarity.

Link to this project
Member project Research

CNN Predictor for Reversible Data Hiding in Encrypted Images

Aditya Kumar Chaudhary

M.Tech thesis work on prediction for privacy-preserving image data hiding.

Link to this project
Member project Research

Dataset-distillation tooling

Ayush Kumar

Built experimental dataset-distillation software for data synthesis, evaluation and experiment tracking.

Link to this project
Member project Research

Design and Development of Robust Models for Social Media Image Forensics

Meenakshi Diwan

full-time Ph.D. research under Rajeev Kumar, with Anurag Goel as co-supervisor at DTU.

Link to this project
Member project Research

Doctoral thesis research — Development of Data Hiding Methods for Content Protection in Medical Domain

Dr. Sonal Gandhi

research on reversible data-hiding and deep-learning methods for protecting medical-image content.

Link to this project
Member project Research

Enabling Technologies for Trustworthy Artificial Intelligence

Nikhil Gupta

Ph.D. research on adversarial robustness and trustworthy AI, including reversible adversarial perturbations.

Link to this project
Member project Research

Face Anti-Spoofing Detection System

Priyanshu Yadav

developed a MobileNetV2-based presentation-attack detection pipeline on the LCC FASD dataset, with augmentation and preprocessing for varied spoofing conditions.

Link to this project
Member project Research

High-Capacity Reversible Data Hiding in Encrypted Images

Ajit Kumar Yadav

DTU-recorded M.Tech (Research) thesis topic aligned with his two IEEE ICSCCC 2026 papers.

Link to this project
Member project Research

Image-prediction and inpainting experiments

Ayush Kumar

Built experimental image-prediction and inpainting software, including training, checkpointing and evaluation tools, using third-party methods and libraries.

Link to this project
Member project Research

MASUL

Dr Pallavi Ranjan

A Data-Driven Game-Based Learning System for Ethical AI Use in Academia — UOW Dubai-funded project listed in 2025; AED 29,250 over 18 months. Pallavi Ranjan is a listed investigator alongside Farhad Oroumchian, Zeenath Reza Khan, Nkqubela Ruxwana, Dare Pitan, Veronika Krasnican and Mohamed Fawaz. Supports the Swiss MENA Project with CurveUp and the European Network for Academic Integrity. Current completion status is not stated.

Link to this project
Member project Research

Model-pruning and adapter-recovery tooling

Ayush Kumar

Built experimental pipelines for model pruning and adapter-based recovery.

Link to this project
Browse all 74 profile project records
Explore the research areas that connect this work.

Security of Neural Networks

Defending deep models against adversarial examples, backdoor and data-poisoning attacks — and understanding when and why they fail.

Adversarial MLBackdoor DefenseRobustness

Data Hiding & Watermarking

Reversible data hiding in encrypted images, image and text steganography, and robust watermarking for ownership and integrity.

Reversible Data HidingSteganographyWatermarking

Multimedia Forensics

Detecting manipulated and GAN-generated media — deepfakes, splicing and median-filtering traces.

Deepfake DetectionImage ForensicsAuthenticity

Trustworthy & Private AI

Federated and privacy-preserving learning, explainable and trustworthy models, and methods for limiting the disclosure of training data.

Federated LearningExplainable AIPrivacy