What is he best known for?
The fields of study he is best known for:
- Cryptography
- Algorithm
- Artificial intelligence
His scientific interests lie mostly in Differential privacy, Computer security, Incentive, Privacy software and Machine learning.
Ilya Mironov interconnects Equivalence, Theoretical computer science, Secret sharing and Row in the investigation of issues within Differential privacy.
His Computer security research includes elements of Payment, Overhead, Peer-to-peer and Reinforcement learning.
His Incentive research includes themes of Computation and The Internet.
His studies in Privacy software integrate themes in fields like Inference and Data mining.
His Machine learning study integrates concerns from other disciplines, such as Information sensitivity, Private information retrieval and Artificial intelligence.
His most cited work include:
- Deep Learning with Differential Privacy (1299 citations)
- Our data, ourselves: privacy via distributed noise generation (1005 citations)
- Differentially private recommender systems: Building privacy into the Netflix Prize contenders (511 citations)
What are the main themes of his work throughout his whole career to date?
Ilya Mironov spends much of his time researching Theoretical computer science, Differential privacy, Cryptography, Computer security and Encryption.
His Theoretical computer science study combines topics in areas such as Hash function, Cryptanalysis and Protocol.
His study in Differential privacy is interdisciplinary in nature, drawing from both Machine learning, Recommender system, Artificial intelligence and Privacy software.
His study on Artificial neural network is often connected to Noise as part of broader study in Machine learning.
The Oblivious transfer research Ilya Mironov does as part of his general Cryptography study is frequently linked to other disciplines of science, such as Impossibility, therefore creating a link between diverse domains of science.
His research in Computer security focuses on subjects like Incentive, which are connected to Peer-to-peer, Payment and Reinforcement learning.
He most often published in these fields:
- Theoretical computer science (33.71%)
- Differential privacy (29.21%)
- Cryptography (22.47%)
What were the highlights of his more recent work (between 2016-2021)?
- Differential privacy (29.21%)
- Data mining (7.87%)
- Artificial intelligence (8.99%)
In recent papers he was focusing on the following fields of study:
His main research concerns Differential privacy, Data mining, Artificial intelligence, Analytics and Noise.
His research integrates issues of Computer security, Anonymity, Recommender system, Privacy software and Range in his study of Differential privacy.
His Privacy software research is multidisciplinary, incorporating perspectives in Data modeling and Private information retrieval.
His research on Artificial intelligence often connects related areas such as Machine learning.
The Machine learning study combines topics in areas such as Privacy by Design, Information privacy, Internet privacy and Training set.
His work in Analytics tackles topics such as Profiling which are related to areas like Secret sharing, Cryptography and Data science.
Between 2016 and 2021, his most popular works were:
- Rényi Differential Privacy (307 citations)
- Prochlo: Strong Privacy for Analytics in the Crowd (136 citations)
- Scalable Private Learning with PATE. (96 citations)
In his most recent research, the most cited papers focused on:
- Cryptography
- Algorithm
- Artificial intelligence
Ilya Mironov mostly deals with Differential privacy, Artificial intelligence, Noise, Scalability and Data mining.
His work deals with themes such as Computer security and Privacy software, which intersect with Differential privacy.
His Computer security study incorporates themes from Overhead and Corollary.
The various areas that Ilya Mironov examines in his Privacy software study include Analytics, Secret sharing and Profiling.
His Artificial intelligence research is multidisciplinary, incorporating elements of Disjoint sets, Machine learning and Personally identifiable information.
His Data mining research incorporates elements of Normalization, Deep learning and Curse of dimensionality.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
