no code implementations • 23 Jan 2024 • Chandrakanth Gudavalli, Erik Rosten, Lakshmanan Nataraj, Shivkumar Chandrasekaran, B. S. Manjunath
Content creation and image editing can benefit from flexible user controls.
1 code implementation • 4 Nov 2022 • Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Satish Chikkagoudar, Shivkumar Chandrasekaran, B. S. Manjunath
The number of malware is constantly on the rise.
no code implementations • 22 May 2022 • Vamshi C. Madala, Shivkumar Chandrasekaran, Jason Bunk
A priori theories explaining the generalization performances of deep neural networks have mostly ignored the convolutionality aspect and do not specify why CNNs are able to seemingly overcome curse of dimensionality on computer vision tasks like image classification where the image dimensions are in thousands.
no code implementations • 8 Nov 2021 • Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Tejaswi Nanjundaswamy, Satish Chikkagoudar, Shivkumar Chandrasekaran, B. S. Manjunath
In this paper, we propose a novel and orthogonal malware detection (OMD) approach to identify malware using a combination of audio descriptors, image similarity descriptors and other static/statistical features.
no code implementations • 8 Nov 2021 • Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Satish Chikkagoudar, Shivkumar Chandrasekaran, B. S. Manjunath
Malicious PDF documents present a serious threat to various security organizations that require modern threat intelligence platforms to effectively analyze and characterize the identity and behavior of PDF malware.
no code implementations • 4 Sep 2021 • Lakshmanan Nataraj, Chandrakanth Gudavalli, Tajuddin Manhar Mohammed, Shivkumar Chandrasekaran, B. S. Manjunath
In this paper, we propose a two-step method to detect and localize seam carved images.
no code implementations • 28 Aug 2021 • Chandrakanth Gudavalli, Erik Rosten, Lakshmanan Nataraj, Shivkumar Chandrasekaran, B. S. Manjunath
Seam carving is a popular technique for content aware image retargeting.
no code implementations • 12 Apr 2021 • Lakshmanan Nataraj, Michael Goebel, Tajuddin Manhar Mohammed, Shivkumar Chandrasekaran, B. S. Manjunath
While most detection methods in literature focus on detecting a particular type of manipulation, it is challenging to identify doctored images that involve a host of manipulations.
no code implementations • 22 Mar 2021 • Jason Bunk, Srinjoy Chattopadhyay, B. S. Manjunath, Shivkumar Chandrasekaran
Mixup is a procedure for data augmentation that trains networks to make smoothly interpolated predictions between datapoints.
1 code implementation • 19 Mar 2021 • Michael Goebel, Jason Bunk, Srinjoy Chattopadhyay, Lakshmanan Nataraj, Shivkumar Chandrasekaran, B. S. Manjunath
Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment.
1 code implementation • 26 Jan 2021 • Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Satish Chikkagoudar, Shivkumar Chandrasekaran, B. S. Manjunath
Motivated by the visual similarity of these images for different malware families, we compare our deep neural network models with standard image features like GIST descriptors to evaluate the performance.
no code implementations • 13 Dec 2020 • Abhejit Rajagopal, Vamshi C. Madala, Shivkumar Chandrasekaran, Peder E. Z. Larson
We study generalization in deep learning by appealing to complexity measures originally developed in approximation and information theory.
no code implementations • 18 Oct 2020 • Sudipta Paul, Shivkumar Chandrasekaran, B. S. Manjunath, Amit K. Roy-Chowdhury
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available.
no code implementations • 20 Jul 2020 • Michael Goebel, Lakshmanan Nataraj, Tejaswi Nanjundaswamy, Tajuddin Manhar Mohammed, Shivkumar Chandrasekaran, B. S. Manjunath
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 computers.
no code implementations • 15 Mar 2019 • Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Shivkumar Chandrasekaran, Arjuna Flenner, Jawadul H. Bappy, Amit K. Roy-Chowdhury, B. S. Manjunath
The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images.
no code implementations • 6 Jun 2018 • Abhejit Rajagopal, Shivkumar Chandrasekaran, Hrushikesh N. Mhaskar
A new design methodology for neural networks that is guided by traditional algorithm design is presented.
no code implementations • 9 Feb 2018 • Tajuddin Manhar Mohammed, Jason Bunk, Lakshmanan Nataraj, Jawadul H. Bappy, Arjuna Flenner, B. S. Manjunath, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury, Lawrence Peterson
Realistic image forgeries involve a combination of splicing, resampling, cloning, region removal and other methods.
1 code implementation • 3 Jul 2017 • Jason Bunk, Jawadul H. Bappy, Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Arjuna Flenner, B. S. Manjunath, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury, Lawrence Peterson
In this paper, we propose two methods to detect and localize image manipulations based on a combination of resampling features and deep learning.