Prith Sengupta

Prith Sengupta

Postdoctoral Fellow and Teaching Faculty at CMU

Posts by Collection

portfolio

publications

Source anonymization of digital images: a counter–forensic attack on PRNU based source identification techniques

Published in Annual Conference on Digital Forensics, Security and Law, 2017

A lot of photographers and human rights advocates need to hide their identity while sharing their images on the internet. Hence, source-anonymization of digital images has become a critical issue in the present digital age. The current literature contains a few digital forensic techniques for” source-identification” of digital images, one of the most efficient of them being Photo-Response Non-Uniformity (PRNU) sensor noise pattern based source detection. PRNU noise pattern being unique to every digital camera, such techniques prove to be highly robust way of sourceidentification. In this paper, we propose a counter-forensic technique to mislead this PRNU sensor noise pattern based source-identification, by using a median filter to suppress PRNU noise in an image, iteratively. Our experimental results prove that the proposed method achieves considerably higher degree of source anonymity, measured as an inverse of Peak-to-Correlation Energy (PCE) ratio, as compared to the state-of-the-art.

Download here

Classification of Computer Generated and Natural Images based on Efficient Deep Convolutional Recurrent Attention Model

Published in CVPR Workshops, 2019

Most state-of-the-art techniques of distinguishing natural images and computer generated images based on handcrafted feature and Convolutional Neural Network require processing of the entire input image pixels uniformly. As a result, such techniques usually require extensive computation time and memory, that scale linearly with the size of the input image in terms of number of pixels. In this paper, we deploy an efficient Deep Convolutional Recurrent Attention model with relatively less number of parameters, to distinguish between natural and computer generated images. The proposed model uses a glimpse network to locally process a sequence of selected image regions; hence, the number of parameters and computation time can be controlled effectively. We also adopt a local-to-global strategy by training image patches and classifying full-sized images using the simple majority voting rule. The proposed approach achieves superior classification accuracy compared to recently proposed approaches based on deep learning.

Download here

A Review of and Some Results for Ollivier–Ricci Network Curvature

Published in Mathematics, 2020

Characterizing topological properties and anomalous behaviors of higher-dimensional topological spaces via notions of curvatures is by now quite common in mainstream physics and mathematics, and it is therefore natural to try to extend these notions from the non-network domains in a suitable way to the network science domain. In this article we discuss one such extension, namely Ollivier’s discretization of Ricci curvature. We first motivate, define and illustrate the Ollivier–Ricci Curvature. In the next section we provide some “not-previously-published” bounds on the exact and approximate computation of the curvature measure. In the penultimate section we review a method based on the linear sketching technique for efficient approximate computation of the Ollivier–Ricci network curvature. Finally in the last section we provide concluding remarks with pointers for further reading.

Download here

Ricci Curvature and Ricci Flow for Graphs and Hypergraphs

Published in PhD Dissertation, University of Illinois at Chicago, 2024

My doctoral dissertation, advised by Bhaskar DasGupta, on discretizing notions of curvature and curvature-driven flows for network-theoretic structures. The thesis covers discrete curvature on graphs and hypergraphs, Ollivier-Ricci curvature, Ricci flow, and the extension of Ricci flow to hypergraphs, with applications to identifying influential structures in real-world networks.

Download here

Finding Influential Cores via Normalized Ricci Flows in Directed and Undirected Hypergraphs with Applications

Published in Physical Review E, 2025

Many biological and social systems are naturally represented as edge-weighted directed or undirected hypergraphs since they exhibit group interactions involving three or more system units as opposed to pairwise interactions that can be incorporated in graph-theoretic representations. However, finding influential cores in hypergraphs is still not as extensively studied as their graph-theoretic counter-parts. To this end, we develop and implement a hypergraph-curvature guided discrete time diffusion process with suitable topological surgeries and edge-weight re-normalization procedures for both undirected and directed weighted hypergraphs to find influential cores. We successfully apply our framework for directed hypergraphs to seven metabolic hypergraphs and our framework for undirected hypergraphs to two social (co-authorship) hypergraphs to find influential cores, thereby demonstrating the practical feasibility of our approach. In addition, we prove a theorem showing that a certain edge weight re-normalization procedure in a prior research work for Ricci flows for edge-weighted graphs has the undesirable outcome of modifying the edge-weights to negative numbers, thereby rendering the procedure impossible to use. To the best of our knowledge, this seems to be one of the first articles that formulates algorithmic approaches for finding core(s) of (weighted or unweighted) directed hypergraphs.

Download here

On analyzing networks via curvature measures: review of methodologies and applications

Published in Convex and Variational Analysis with Applications: In Honor of Terry Rockafellar's 90th Birthday, Springer, 2025

Suitable notions of shapes play a critical role in investigating objects in mathematics, physics and other research areas. Various kinds of curvatures are very natural measures of shapes of higher dimensional objects in mainstream physics and mathematics. However, any attempt to extend notions of these kinds of measures to networks needs to overcome several key challenges. In this article we review several curvature measures for networks such as (i) Gromov-hyperbolic curvature, (ii) extension of discretization of Ricci curvature for polyhedral complexes, and (iii) extension of discretization of Ricci curvature via mass transportation distances, and the corresponding flow technique. We finally review the bioinformatics applications of these measures for several biological networks such as E. coli transcriptional network, metabolic network of M. tuberculosis, protein-protein interaction networks in humans and network of functional correlations between brain regions for attention deficit hyperactivity disorder.

Download here

talks

teaching

Lead Instructor — Mathematical Foundations of Computing (CS 151)

Undergraduate Course, University of Illinois at Chicago, Department of Computer Science, 2021

Instructor of record for Mathematical Foundations of Computing (CS 151), Summer 2021. Independently developed all course materials and taught a fully remote class of 50 students, including designing, administering, and grading all exams, and coordinating a supporting teaching assistant.