Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Anjali Kaushik

dblp:134/7347 · DBLP profile ↗
← Back
3ranked-venue papers
0as first author
1since 2021 · last 2025
0000-0001-6782-5742ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 since 2021Security and privacy · 1Databases, data management, data science and information retrieval · 1 · 1 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Network and information security
1 paper
Privacy and data protection · 100%
Artificial intelligence
1 paper
Generative modeling · 100%

Topics — the 3 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Privacy and data protection
privacy-preserving data analysis
0.912025
DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming · ICDM 2025
Privacy and data protection › privacy-preserving data processing
privacy-preserving data transformation
0.912025
DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming · ICDM 2025
Machine learning › Generative modeling
variational autoencoder
0.312025
DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming · ICDM 2025

Methods — techniques the papers use, named apart from their topics

variational LSTM seq2seq · 1.7reinforcement learning · 1.7causal disentanglement · 1.7adversarial learning · 1.7
YearPublicationVenuePosition
2025 DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming
abstract
In real-world applications, domain data often contains identifiable or sensitive attributes, is subject to strict regulations (e.g., HIPAA, GDPR), and requires explicit data feature engineering for interpretability and transparency. Existing feature engineering primarily focuses on advancing downstream task performance, often risking privacy leakage. We generalize this learning task under such new requirements as Privacy-Preserving Data Reprogramming (PPDR): given a dataset, transforming features to maximize target attribute prediction accuracy while minimizing sensitive attribute prediction accuracy. PPDR poses challenges for existing systems: 1) generating high-utility feature transformations without being overwhelmed by a large search space, and 2) disentangling and eliminating sensitive information from utility-oriented features to reduce privacy inferability. To tackle these challenges, we propose DELTA, a two-phase variational disentangled generative learning framework. Phase I uses policy-guided reinforcement learning to discover feature transformations with downstream task utility, without any regard to privacy inferability. Phase II employs a variational LSTM seq2seq encoder-decoder with a utility-privacy disentangled latent space design and adversarial-causal disentanglement regularization to suppress privacy signals during feature generation. Experiments on eight datasets show DELTA improves predictive performance by ~ 9.3% and reduces privacy leakage by ~ 35%, demonstrating robust, privacy-aware data transformation. The code repository is available at https://github.com/arunvignesh28/DELTA-PGFT.
Arun Vignesh Malarkkan, Haoyue Bai 0002, Anjali Kaushik, Yanjie Fu
ICDM3
2020 ATOM: HMD-VR Interface to Learn Atomic Structure, Bonding and Historical Research Experiments
abstract
Head-Mounted Displays (HMDs) based Virtual Reality (VR) has shown promising results in training and education. We present ATOM, an HMD-VR interface to educate students about atoms, atomic structures and historical research experiments conducted in understanding atomic structures. ATOM is designed to complement the classroom learning for grade 9 students through an interactive and practice-based learning experience. Preliminary evaluation with 10 students revealed higher interest, increase engagement and playfulness. The students also pointed out a few difficult user interactions.
Shimmila Bhowmick, Anjali Kaushik, Rohan Bhatia, Keyur Sorathia
VRST2
2017 State transgression on electronic expression: is it for real?
abstract
Purpose Cyberspace is a virtual environment where instantaneous communications are initiated and consumed using computer networks without any natural or artificial boundaries. These communications are not only an exchange of information but also a catharsis on the socio-political environment of the real world. This explosion of electronic expression is often detrimental to the traditional secretive maneuvers of nation states and the exercise of its power. Unable to come to terms with the new reality nation states through legislative action or otherwise attempt to assert its sovereignty in the space that has no political and societal boundaries. This may lead to an encroachment on basic human rights that often have constitutional guarantees in the real world but may be violated in the online milieu. This paper aims to investigate this issue in detail and evaluate whether nation states are using cyber-security as a propaganda tool to transgress on electronic expression. Design/methodology/approach The Website of the UN Office of the High Commissioner for Human Rights states “In December 2013, the United Nations General Assembly adopted resolution 68/167, which expresses deep concern at the negative impact that surveillance and interception of communications may have on human rights”. It further says “The General Assembly called on all States to review their procedures, practices and legislation related to communications surveillance, interception and collection of personal data and emphasized the need for States to ensure the full and effective implementation of their obligations under international human rights law”. With this development, this paper seeks to unravel the role of nation states in using cybersecurity as a propaganda tool by raising the specter of threat to national security and economic wellbeing. The paper is based on exploratory research with data compilation from secondary sources. To collect data, various research papers, books and journals have been referenced and data available in public domain has been accumulated. Findings This paper has tried to unravel state action on cyberspace which often runs counter to the concept of civil liberties. It indicates that in terms of both national security and economic impact, cybercrime represent a very nominal threat vector. Also, cybercrime as compared with other forms of crime is again nominal. Finally, cyber laws and policies of different countries need to be more nuanced such as to allow space for civil liberties. Overall, the propaganda surrounding the malaise of cybercrime seems to be more hype than real. We already have examples of countries who have transgressed into electronic expression in cyber space. Therefore, UN has a valid reason to raise a red flag on this unfolding issue. Originality/value This paper was published at 21st Americas Conference of Information Systems held at Puerto Rico, USA, between August 13-15, 2015 (AMCIS, 2015). The authors of this paper seek review by Editors of the Journal for Republication of original work. The authors have taken cognizance of the Originality Guidelines for Emerald published at this URL www.emeraldgrouppublishing.com/authors/writing/originality.htm
Argha Ray, Anjali Kaushik
Inf. Comput. Secur.2