Publications
- This research publication analyzes the contemporary interpretation of Privacy-Preserving Machine Learning and the significance it holds in myriad settings.
- It covers prevalent types of privacy attacks on ML systems like inferences of the membership, input, parameter, and property, along with examining some privacy-enhancing techniques such as differential privacy, federated learning, and synthetic data along with modern-day advancements like dataset condensation among others.
- It also highlights some of the recent policy developments to regulate data protection and privacy worldwide and how that is shaping the industry. The goal is to ignite the public dialogue regarding privacy impacts, ethical consequences, fairness, and real-world harms of non-privacy-compliant ML systems.
- Published as a chapter in Springer’s latest book titled Data Protection in a Post-Pandemic Society: Laws, Regulations, Best Practices and Recent Solutions.
- This research publication analyzes the definition and forms of fake news on social media and is a comparative study of deep learning models to identify phony information, verify the validity of various claims and facts, catch fake content, and so on.
- It discusses the limitations of deep learning with insights into the fairness, interpretability, and accountability of fake news detection algorithms.
- Published in Springer book titled ‘Deep Learning for Social Media Data Analytics’ as a part of their popular book series Studies in Big Data.
- The book introduces the readers to the first act of Machine Learning, Dataset Curation. This step-by-step guide accompanies code examples in Python from the extraction of real-world datasets and practical tips to identify valuable information on the web. In addition, it also dives deep into how data fits into the Machine Learning ecosystem and highlights the impact of data-centric approaches on ML system’s performance.
- To date, delivered 25+ talks across the US and beyond to champion the importance of data in Machine Learning under the #DataForML campaign.
- Endorsed by leading ML experts in Academia and Industry; Forewords by: Julian McAuley, Laurence Moroney, and Mengting Wan.
- It is available both as a paperback and Kindle eBook, grab a copy here!
- This ACM publication focuses on the spatial interface of agent-based simulation platforms to visualize the evolution of the system through time. It analyses state-of-the-art, scrutinizing in terms of programming flexibility, extensibility, portability, scalability, and interaction. Subsequently, it highlights the efforts in building an open-source extension for CORMAS’ spatial interface in Pharo.
- Presented at the 12th edition of the International Workshop on Smalltalk Technologies held in Maribor, Slovenia.
- As an Open Source Developer, contributed to this book published by Square Bracket Associates that introduces the Pharo programming environment, the language and the associated tools. It also puts forward common practices of the Pharo environment with a focus on object-oriented design.
