Deepesh Chaudhari

Deepesh Chaudhari is a Founder and CEO of BlockStash Intelligence. He completed his MTech in computer science from IIT-Kanpur in 2021, with guidance from Prof. Sandeep Shukla. Prior to that, he completed his BTech at Allenhouse Group of Colleges, Kanpur in 2018. During his master's program, He focused on the detection of malicious accounts on the Bitcoin blockchain, leading to the publication of a research paper. Building upon his thesis work, he started a startup BlockStash Intelligence. where he is currently involved in the development of an analytic tool for investigating and monitoring illicit activities related to cryptocurrencies.

Research & Publicaitons

Towards Malicious address identification in Bitcoin

The temporal aspect of blockchain transactions enables us to study the address's behavior and detect if it is involved in any illicit activity. However, due to the concept of change addresses (used to thwart replay attacks), temporal aspects are not directly applicable in the Bitcoin blockchain. Several pre-processing steps should be performed before such temporal aspects are utilized. We are motivated to study the Bitcoin transaction network and use the temporal features ... such as burst, attractiveness, and inter-event time along with several graph-based properties such as the degree of node and clustering coefficient to validate the applicability of already existing approaches known for other cryptocurrency blockchains on the Bitcoin blockchain. We generate the temporal and non-temporal feature set and train the Machine Learning (ML) algorithm over different temporal granularities to validate the state-of-the-art methods. We study the behavior of the addresses over different time granularities of the dataset. We identify that after applying change-address clustering, in Bitcoin, existing temporal features can be extracted and ML approaches can be applied. A comparative analysis of results show that the behavior of addresses in Ethereum and Bitcoin is similar with respect to in-degree, out-degree and inter-event time. Further, we identify 3 suspects that showed malicious behavior across different temporal granularities. These suspects are not marked as malicious in Bitcoin. Read more

This work was done under the guidance of Prof. Sandeep Shukla and Dr. Rachit Agarwal.

[D. Chaudhari, R. Agarwal and S. K. Shukla, "Towards Malicious address identification in Bitcoin," 2021 IEEE International Conference on Blockchain (Blockchain), 2021, pp. 425-432, doi: 10.1109/Blockchain53845.2021.00066.]

Course projects

Course projects

  • Performed feature analysis on executables, compared different ML models to find benign and malware and get best performance by Random Forest Model.
  • Technology used: Python and Linux shell script.
(from Feb'20- till Mar'20)
  • Implemented a load balancer to distribute traffic on multiple servers based on request.
  • Technology used: core PHP, HTML5, CSS, MySQL and Docker.
(from Aug'19- till Sept'19 )
  • Designed a highly available website (replicate ping-echo and active redundancy) hosted on multiple servers.
  • Technology used: PHP, HTML, CSS, MySQL and Docker
(from Sept'19- till Oct'19 )
  • Recommendation system which recommends top 5 items, Implemented Bonsai - Diverse and Shallow Trees for Extreme Multi-Label Classification and used K-means clustering for label partition at each node.
  • Technology used: Python and C++

( from Aug'19- till Dec'19 )
  • We trained a convolutional neural network model to identify each character in the image(CAPTCHA) which involves extraction of individual characters from given CAPTCHA images which are then used for training the model.
  • Technology used: Python

(from Oct'19-till Nov'19 )
  • Trained a POS tagging model using training corpus containing POS tags for english sentences, used to calculate F-score and predict tagging, Designed a bottom up parser to parse sentences using given grammar.
  • Technology used: Python and C++

( from Jan'20- till Feb'20 )
  • Used SAT solver(sat4j) to detect tampering in manufactured circuits and to test equality of given firewalls.
  • Also used SMT solver(z3) solvers to solve various problems including sum-sudoku, which is a slightly modified version of the usual sudoku.
  • Technology used: Scala

( from Feb'20- till Mar'20 )

Work Experience

Internship in Aditya Birla Group 2016-2017

There, I worked in two project.
  • company survey management,
  • A small scale CRM(customer relationship management).

both project developed in JSP(java server page) technology.



Completed MTech in computer science from IIT Kanpur

I completed my class-XII in 2014 from Saraswati Vidya Mandir Inter College, Kanpur

I completed high school in 2012 from M.V.M inter college, Kanpur.

My Specialty


These are some tools and technologies with which I work and love to make new stuff, still learning some new skills to make stuff more powerful, efficient, and worthy...



Machine learning




SEO (Search Engine Optimization)


Linux Shell script

Graphic Design

Web Design



Get in Touch

Contact | |

Room no 406, Technopark Building, IIT-Kanpur 208016