Search Results for author: Terrance E. Boult

Found 27 papers, 5 papers with code

Enhanced Performance of Pre-Trained Networks by Matched Augmentation Distributions

no code implementations19 Jan 2022 Touqeer Ahmad, Mohsen Jafarzadeh, Akshay Raj Dhamija, Ryan Rabinowitz, Steve Cruz, Chunchun Li, Terrance E. Boult

Specifically, we demonstrate that running inference on the center crop of an image is not always the best as important discriminatory information may be cropped-off.

Self-Supervised Features Improve Open-World Learning

1 code implementation15 Feb 2021 Akshay Raj Dhamija, Touqeer Ahmad, Jonathan Schwan, Mohsen Jafarzadeh, Chunchun Li, Terrance E. Boult

This paper identifies the flaws in existing open-world learning approaches and attempts to provide a complete picture in the form of \textbf{True Open-World Learning}.

Incremental Learning Out-of-Distribution Detection

A Review of Open-World Learning and Steps Toward Open-World Learning Without Labels

1 code implementation25 Nov 2020 Mohsen Jafarzadeh, Akshay Raj Dhamija, Steve Cruz, Chunchun Li, Touqeer Ahmad, Terrance E. Boult

Open-world learning is related to but also distinct from a multitude of other learning problems and this paper briefly analyzes the key differences between a wide range of problems including incremental learning, generalized novelty discovery, and generalized zero-shot learning.

Generalized Zero-Shot Learning Image Classification +1

Adversarial Attack on Deep Learning-Based Splice Localization

1 code implementation17 Apr 2020 Andras Rozsa, Zheng Zhong, Terrance E. Boult

Regarding image forensics, researchers have proposed various approaches to detect and/or localize manipulations, such as splices.

Adversarial Attack Adversarial Robustness +1

To Beta or Not To Beta: Information Bottleneck for DigitaL Image Forensics

no code implementations11 Aug 2019 Aurobrata Ghosh, Zheng Zhong, Steve Cruz, Subbu Veeravasarapu, Terrance E. Boult, Maneesh Singh

We propose an innovative method to formulate the issue of localizing manipulated regions in an image as a deep representation learning problem using the Information Bottleneck (IB), which has recently gained popularity as a framework for interpreting deep neural networks.

Image Forensics Representation Learning +1

Improved Adversarial Robustness by Reducing Open Space Risk via Tent Activations

no code implementations7 Aug 2019 Andras Rozsa, Terrance E. Boult

On the CIFAR-10 dataset, our approach improves the average accuracy against the six white-box adversarial attacks to 73. 5% from 41. 8% achieved by adversarial training via PGD.

Adversarial Robustness

Reducing Network Agnostophobia

4 code implementations NeurIPS 2018 Akshay Raj Dhamija, Manuel Günther, Terrance E. Boult

Agnostophobia, the fear of the unknown, can be experienced by deep learning engineers while applying their networks to real-world applications.

Facial Attributes: Accuracy and Adversarial Robustness

no code implementations4 Jan 2018 Andras Rozsa, Manuel Günther, Ethan M. Rudd, Terrance E. Boult

Facial attributes, emerging soft biometrics, must be automatically and reliably extracted from images in order to be usable in stand-alone systems.

Adversarial Robustness General Classification

The Unconstrained Ear Recognition Challenge

no code implementations23 Aug 2017 Žiga Emeršič, Dejan Štepec, Vitomir Štruc, Peter Peer, Anjith George, Adil Ahmad, Elshibani Omar, Terrance E. Boult, Reza Safdari, Yuxiang Zhou, Stefanos Zafeiriou, Dogucan Yaman, Fevziye I. Eyiokur, Hazim K. Ekenel

In this paper we present the results of the Unconstrained Ear Recognition Challenge (UERC), a group benchmarking effort centered around the problem of person recognition from ear images captured in uncontrolled conditions.

Person Recognition

Adversarial Robustness: Softmax versus Openmax

no code implementations5 Aug 2017 Andras Rozsa, Manuel Günther, Terrance E. Boult

Deep neural networks (DNNs) provide state-of-the-art results on various tasks and are widely used in real world applications.

Adversarial Robustness Open Set Learning

Toward Open-Set Face Recognition

no code implementations3 May 2017 Manuel Günther, Steve Cruz, Ethan M. Rudd, Terrance E. Boult

In this paper, we address the widespread misconception that thresholding verification-like scores is a good way to solve the open-set face identification problem, by formulating an open-set face identification protocol and evaluating different strategies for assessing similarity.

Face Identification Face Recognition +1

Towards Robust Deep Neural Networks with BANG

no code implementations1 Dec 2016 Andras Rozsa, Manuel Gunther, Terrance E. Boult

Machine learning models, including state-of-the-art deep neural networks, are vulnerable to small perturbations that cause unexpected classification errors.

Data Augmentation General Classification

LOTS about Attacking Deep Features

no code implementations18 Nov 2016 Andras Rozsa, Manuel Günther, Terrance E. Boult

We demonstrate that iterative LOTS is very effective and show that systems utilizing deep features are easier to attack than the end-to-end network.

Adversarial Robustness

AFFACT - Alignment-Free Facial Attribute Classification Technique

no code implementations18 Nov 2016 Manuel Günther, Andras Rozsa, Terrance E. Boult

Using an ensemble of three ResNets, we obtain the new state-of-the-art facial attribute classification error of 8. 00% on the aligned images of the CelebA dataset.

Data Augmentation Facial Attribute Classification +1

Automated Big Text Security Classification

no code implementations21 Oct 2016 Khudran Alzhrani, Ethan M. Rudd, Terrance E. Boult, C. Edward Chow

To analyze the ACESS system, we constructed a novel dataset, containing formerly classified paragraphs from diplomatic cables made public by the WikiLeaks organization.

General Classification

Are Accuracy and Robustness Correlated?

no code implementations14 Oct 2016 Andras Rozsa, Manuel Günther, Terrance E. Boult

In this paper, we perform experiments on various adversarial example generation approaches with multiple deep convolutional neural networks including Residual Networks, the best performing models on ImageNet Large-Scale Visual Recognition Challenge 2015.

General Classification Object Recognition

Assessing Threat of Adversarial Examples on Deep Neural Networks

no code implementations13 Oct 2016 Abigail Graese, Andras Rozsa, Terrance E. Boult

Deep neural networks are facing a potential security threat from adversarial examples, inputs that look normal but cause an incorrect classification by the deep neural network.

Binarization General Classification

Specialized Support Vector Machines for Open-set Recognition

no code implementations13 Jun 2016 Pedro Ribeiro Mendes Júnior, Terrance E. Boult, Jacques Wainer, Anderson Rocha

In the open-set scenario, however, a test sample can belong to none of the known classes and the classifier must properly reject it by classifying it as unknown.

General Classification Open Set Learning +1

Are Facial Attributes Adversarially Robust?

no code implementations18 May 2016 Andras Rozsa, Manuel Günther, Ethan M. Rudd, Terrance E. Boult

We show that FFA generates more adversarial examples than other related algorithms, and that DCNNs for certain attributes are generally robust to adversarial inputs, while DCNNs for other attributes are not.

Facial Attribute Classification General Classification

PARAPH: Presentation Attack Rejection by Analyzing Polarization Hypotheses

no code implementations10 May 2016 Ethan M. Rudd, Manuel Gunther, Terrance E. Boult

Thus, there is great demand for an effective and low cost system capable of rejecting such attacks. To this end we introduce PARAPH -- a novel hardware extension that exploits different measurements of light polarization to yield an image space in which presentation media are readily discernible from Bona Fide facial characteristics.

Adversarial Diversity and Hard Positive Generation

no code implementations5 May 2016 Andras Rozsa, Ethan M. Rudd, Terrance E. Boult

Finally, we demonstrate on LeNet and GoogLeNet that fine-tuning with a diverse set of hard positives improves the robustness of these networks compared to training with prior methods of generating adversarial images.

Data Augmentation

A Survey of Stealth Malware: Attacks, Mitigation Measures, and Steps Toward Autonomous Open World Solutions

no code implementations19 Mar 2016 Ethan M. Rudd, Andras Rozsa, Manuel Günther, Terrance E. Boult

While machine learning offers promising potential for increasingly autonomous solutions with improved generalization to new malware types, both at the network level and at the host level, our findings suggest that several flawed assumptions inherent to most recognition algorithms prevent a direct mapping between the stealth malware recognition problem and a machine learning solution.

The Extreme Value Machine

no code implementations19 Jun 2015 Ethan M. Rudd, Lalit P. Jain, Walter J. Scheirer, Terrance E. Boult

It is often desirable to be able to recognize when inputs to a recognition function learned in a supervised manner correspond to classes unseen at training time.

Incremental Learning

Pruning Bayesian Networks for Efficient Computation

no code implementations27 Mar 2013 Michelle Baker, Terrance E. Boult

We define a computationally equivalent subgraph of a Bayesian network.

Cannot find the paper you are looking for? You can Submit a new open access paper.