54 citations · 98 across the 23 of their papers we have counts for
24 papers
CIMGEN: Controlled Image Manipulation by Finetuning Pretrained Generative Models on Limited Data
Chandrakanth Gudavalli, Erik Rosten, Lakshmanan Nataraj +2
Content creation and image editing can benefit from flexible user controls. A common intermediate representation for conditional image generation is a semantic map, that has inform…
MalGrid: Visualization Of Binary Features In Large Malware Corpora
Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Satish Chikkagoudar +2
The number of malware is constantly on the rise. Though most new malware are modifications of existing ones, their sheer number is quite overwhelming. In this paper, we present a n…
CNNs Avoid Curse of Dimensionality by Learning on Patches
Vamshi C. Madala, Shivkumar Chandrasekaran, Jason Bunk
Despite the success of convolutional neural networks (CNNs) in numerous computer vision tasks and their extraordinary generalization performances, several attempts to predict the g…
OMD: Orthogonal Malware Detection Using Audio, Image, and Static Features
Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Tejaswi Nanjundaswamy +3
With the growing number of malware and cyber attacks, there is a need for "orthogonal" cyber defense approaches, which are complementary to existing methods by detecting unique mal…
HAPSSA: Holistic Approach to PDF Malware Detection Using Signal and Statistical Analysis
Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Satish Chikkagoudar +2
Malicious PDF documents present a serious threat to various security organizations that require modern threat intelligence platforms to effectively analyze and characterize the ide…
Seam Carving Detection and Localization using Two-Stage Deep Neural Networks
Lakshmanan Nataraj, Chandrakanth Gudavalli, Tajuddin Manhar Mohammed +2
Seam carving is a method to resize an image in a content aware fashion. However, this method can also be used to carve out objects from images. In this paper, we propose a two-step…
SeeTheSeams: Localized Detection of Seam Carving based Image Forgery in Satellite Imagery
Chandrakanth Gudavalli, Erik Rosten, Lakshmanan Nataraj +2
Seam carving is a popular technique for content aware image retargeting. It can be used to deliberately manipulate images, for example, change the GPS locations of a building or in…
Minimal Rank Completions for Overlapping Blocks
Ethan N. Epperly, Nithin Govindarajan, Shivkumar Chandrasekaran
We consider the multi-objective optimization problem of choosing the bottom left block-entry of a block lower triangular matrix to minimize the ranks of all block sub-matrices. We…
Holistic Image Manipulation Detection using Pixel Co-occurrence Matrices
Lakshmanan Nataraj, Michael Goebel, Tajuddin Manhar Mohammed +2
Digital image forensics aims to detect images that have been digitally manipulated. Realistic image forgeries involve a combination of splicing, resampling, region removal, smoothi…
Adversarially Optimized Mixup for Robust Classification
Jason Bunk, Srinjoy Chattopadhyay, B. S. Manjunath +1
Mixup is a procedure for data augmentation that trains networks to make smoothly interpolated predictions between datapoints. Adversarial training is a strong form of data augmenta…
Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions
Michael Goebel, Jason Bunk, Srinjoy Chattopadhyay +3
Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment. Automatic reverse engineering of the toolchains behind th…
Malware Detection Using Frequency Domain-Based Image Visualization and Deep Learning
Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Satish Chikkagoudar +2
We propose a novel method to detect and visualize malware through image classification. The executable binaries are represented as grayscale images obtained from the count of N-gra…
Predicting Generalization in Deep Learning via Local Measures of Distortion
Abhejit Rajagopal, Vamshi C. Madala, Shivkumar Chandrasekaran +1
We study generalization in deep learning by appealing to complexity measures originally developed in approximation and information theory. While these concepts are challenged by th…
Exploiting Context for Robustness to Label Noise in Active Learning
Sudipta Paul, Shivkumar Chandrasekaran, B. S. Manjunath +1
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these…
Detection, Attribution and Localization of GAN Generated Images
Michael Goebel, Lakshmanan Nataraj, Tejaswi Nanjundaswamy +3
Recent advances in Generative Adversarial Networks (GANs) have led to the creation of realistic-looking digital images that pose a major challenge to their detection by humans or c…
Graph-Induced Rank Structures and their Representations
Shivkumar Chandrasekaran, Ethan N. Epperly, Nithin Govindarajan
A new framework is proposed to study rank-structured matrices arising from discretizations of 2D and 3D elliptic operators. In particular, we introduce the notion of a graph-induce…
Detecting GAN generated Fake Images using Co-occurrence Matrices
Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Shivkumar Chandrasekaran +4
The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images. GAN based techniques such as…
Fast Algorithms for Displacement and Low-Rank Structured Matrices
Shivkumar Chandrasekaran, Nithin Govindarajan, Abhejit Rajagopal
This tutorial provides an introduction to the development of fast matrix algorithms based on the notions of displacement and various low-rank structures.
On the approximation of Koopman spectra of measure-preserving flows
Nithin Govindarajan, Ryan Mohr, Shivkumar Chandrasekaran +1
The method of using periodic approximations to compute the spectral decomposition of the Koop- man operator is generalized to the class of measure-preserving flows on compact metri…
Deep Algorithms: designs for networks
Abhejit Rajagopal, Shivkumar Chandrasekaran, Hrushikesh N. Mhaskar
A new design methodology for neural networks that is guided by traditional algorithm design is presented. To prove our point, we present two heuristics and demonstrate an algorithm…
On the approximation of Koopman spectra for measure preserving transformations
Nithin Govindarajan, Ryan Mohr, Shivkumar Chandrasekaran +1
For the class of continuous, measure-preserving automorphisms on compact metric spaces, a procedure is proposed for constructing a sequence of finite-dimensional approximations to…
Boosting Image Forgery Detection using Resampling Features and Copy-move analysis
Tajuddin Manhar Mohammed, Jason Bunk, Lakshmanan Nataraj +6
Realistic image forgeries involve a combination of splicing, resampling, cloning, region removal and other methods. While resampling detection algorithms are effective in detecting…
Detection and Localization of Image Forgeries using Resampling Features and Deep Learning
Jason Bunk, Jawadul H. Bappy, Tajuddin Manhar Mohammed +6
Resampling is an important signature of manipulated images. In this paper, we propose two methods to detect and localize image manipulations based on a combination of resampling fe…
A construction of linear bounded interpolatory operators on the torus
S. Chandrasekaran, H. N. Mhaskar
Let be an integer. Given samples of a smooth function of variables, --periodic in each variable, we consider the problem of constructing a --variate trigono…