arXiv subjects

Chirag Agarwal

Publications and source records attributed to Chirag Agarwal.

61 records · Page 4Linked to original sources

arXiv2020

SAM: The Sensitivity of Attribution Methods to Hyperparameters

Attribution methods can provide powerful insights into the reasons for a classifier's decision. We argue that a key desideratum of an explanation method is its robustness to input hyperparameters which are often randomly set or empirically tuned. High sensitivity to arbitrary hyperparameter choices does not only impede reproducibility but also questions the correctness of an explanation and impairs the trust of end-users. In this paper, we provide a thorough empirical study on the sensitivity of existing attribution methods. We found an alarming trend that many methods are highly sensitive to changes in their common hyperparameters e.g. even changing a random seed can yield a different explanation! Interestingly, such sensitivity is not reflected in the average explanation accuracy scores over the dataset as commonly reported in the literature. In addition, explanations generated for robust classifiers (i.e. which are trained to be invariant to pixel-wise perturbations) are surprisingly more robust than those generated for regular classifiers.

cs.CV↗

arXiv2020

Convergence of backpropagation with momentum for network architectures with skip connections

We study a class of deep neural networks with networks that form a directed acyclic graph (DAG). For backpropagation defined by gradient descent with adaptive momentum, we show weights converge for a large class of nonlinear activation functions. The proof generalizes the results of Wu et al. (2008) who showed convergence for a feed forward network with one hidden layer. For an example of the effectiveness of DAG architectures, we describe an example of compression through an autoencoder, and compare against sequential feed forward networks under several metrics.

cs.CV↗

arXiv2019

Deep Radar Waveform Design for Efficient Automotive Radar Sensing

In radar systems, unimodular (or constant-modulus) waveform design plays an important role in achieving better clutter/interference rejection, as well as a more accurate estimation of the target parameters. The design of such sequences has been studied widely in the last few decades, with most design algorithms requiring sophisticated a priori knowledge of environmental parameters which may be difficult to obtain in real-time scenarios. In this paper, we propose a novel hybrid model-driven and data-driven architecture that adapts to the ever changing environment and allows for adaptive unimodular waveform design. In particular, the approach lays the groundwork for developing extremely low-cost waveform design and processing frameworks for radar systems deployed in autonomous vehicles. The proposed model-based deep architecture imitates a well-known unimodular signal design algorithm in its structure, and can quickly infer statistical information from the environment using the observed data. Our numerical experiments portray the advantages of using the proposed method for efficient radar waveform design in time-varying environments.

eess.SP↗

arXiv2019

A New Parallel Message-distribution Technique for Cost-based Steganography

This paper presents two novel approaches to increase performance bounds of image steganography under the criteria of minimizing distortion. First, in order to efficiently use the images' capacities, we propose using parallel images in the embedding stage. The result is then used to prove sub-optimality of the message distribution technique used by all cost based algorithms including HUGO, S-UNIWARD, and HILL. Second, a new distribution approach is presented to further improve the security of these algorithms. Experiments show that this distribution method avoids embedding in smooth regions and thus achieves a better performance, measured by state-of-the-art steganalysis, when compared with the current used distribution.

cs.MM↗

arXiv2019

Improving Adversarial Robustness by Encouraging Discriminative Features

Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.e. inputs that are specifically crafted by an adversary to cause DNNs to misbehave, questioning the security and reliability of applications. In this paper, we encourage DNN classifiers to learn more discriminative features by imposing a center loss in addition to the regular softmax cross-entropy loss. Intuitively, the center loss encourages DNNs to simultaneously learns a center for the deep features of each class, and minimize the distances between the intra-class deep features and their corresponding class centers. We hypothesize that minimizing distances between intra-class features and maximizing the distances between inter-class features at the same time would improve a classifier's robustness to adversarial examples. Our results on state-of-the-art architectures on MNIST, CIFAR-10, and CIFAR-100 confirmed that intuition and highlight the importance of discriminative features.

cs.CR↗

arXiv2018

An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks

Deep Neural Networks(DNN) have excessively advanced the field of computer vision by achieving state of the art performance in various vision tasks. These results are not limited to the field of vision but can also be seen in speech recognition and machine translation tasks. Recently, DNNs are found to poorly fail when tested with samples that are crafted by making imperceptible changes to the original input images. This causes a gap between the validation and adversarial performance of a DNN. An effective and generalizable robustness metric for evaluating the performance of DNN on these adversarial inputs is still missing from the literature. In this paper, we propose Noise Sensitivity Score (NSS), a metric that quantifies the performance of a DNN on a specific input under different forms of fix-directional attacks. An insightful mathematical explanation is provided for deeply understanding the proposed metric. By leveraging the NSS, we also proposed a skewness based dataset robustness metric for evaluating a DNN's adversarial performance on a given dataset. Extensive experiments using widely used state of the art architectures along with popular classification datasets, such as MNIST, CIFAR-10, CIFAR-100, and ImageNet, are used to validate the effectiveness and generalization of our proposed metrics. Instead of simply measuring a DNN's adversarial robustness in the input domain, as previous works, the proposed NSS is built on top of insightful mathematical understanding of the adversarial attack and gives a more explicit explanation of the robustness.

cs.CR↗

arXiv2017

Convolutional Neural Network Steganalysis's Application to Steganography

This paper presents a novel approach to increase the performance bounds of image steganography under the criteria of minimizing distortion. The proposed approach utilizes a steganalysis convolutional neural network (CNN) framework to understand an image's model and embed in less detectable regions to preserve the model. In other word, the trained steganalysis CNN is used to calculate derivatives of the statistical model of an image with respect to embedding changes. The experimental results show that the proposed algorithm outperforms previous state-of-the-art methods in a wide range of low relative payloads when compared with HUGO, S-UNIWARD, and HILL by the state-of-the-art steganalysis.

cs.MM↗