A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
Adaptive gradient algorithms perform gradient-based updates using the history of gradients and are ubiquitous in training deep neural networks. ...
Empirically, our experiments show that indeed adaptive gradient algorithms outperform their non-adaptive counterparts in GAN training. ...
Generative adversarial nets. In Advances in neural information processing systems, pp. 2672-2680, 2014. Paulina Grnarova, Kfir Y Levy, Aurelien Lucchi, Thomas Hofmann, and Andreas Krause. ...
arXiv:1912.11940v2
fatcat:dttxn2qxqrdurpxrxh6vbd3h7i
Data Augmentation for Intelligent Manufacturing with Generative Adversarial Framework
2019
2019 1st International Conference on Industrial Artificial Intelligence (IAI)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The experimental results illustrate that the latent generative adversarial framework with adaptive moment estimation could generated samples of good quality for non-time series missing data. ...
In addition, the two optimization methods, mini-batch gradient descent and adaptive moment estimation are adopted to tune the parameters. ...
ACKNOWLEDGMENT This research is financially supported by the UK Engineering and Physical Sciences Research Council (EPSRC) under grant EP/P004636/1 'Optimising Energy Management in Industry -OPTEMIN'. ...
doi:10.1109/iciai.2019.8850773
fatcat:jsjnkhbzszgodneookx7mundxu
Understanding the Role of Adversarial Regularization in Supervised Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The key ingredient is a theoretical justification supported by empirical evidence of adversarial acceleration in gradient descent. ...
Despite numerous attempts sought to provide empirical evidence of adversarial regularization outperforming sole supervision, the theoretical understanding of such phenomena remains elusive. ...
In light of deeper understanding, we explore several crucial properties pertaining to adversarial acceleration in gradient descent. ...
arXiv:2010.00522v1
fatcat:lppgu45fzraxxlc7vnupxfhove
Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In order to save the human effort in generating annotations required by state-of-the-art, we propose a fingerprint roi segmentation model which aligns the features of fingerprint images derived from the ...
All the learning based state-of-the-art fingerprint roi segmentation algorithms proposed in the literature are benchmarked on scenarios when both training and testing databases consist of fingerprint images ...
Adversarial Learning Several studies showcase the success of adversarial learning framework in a variety of applications such as image generation [11] , [15] , audio-generation [20] , domain adaptation ...
arXiv:2107.01361v1
fatcat:2377szb4jvdavbghycpk42ibnq
Towards Model-Agnostic Adversarial Defenses using Adversarially Trained Autoencoders
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Adversarial machine learning is a well-studied field of research where an adversary causes predictable errors in a machine learning algorithm through precise manipulation of the input. ...
However, adversarial training is computationally expensive and its improvements are limited to a single model. In this work, we take a first step toward creating a model-agnostic adversarial defense. ...
With such pervasive use, it is critical to understand and address the vulnerabilities associated with machine learning algorithms so as to mitigate the risks in real systems. ...
arXiv:1909.05921v3
fatcat:jq7rq4pgtnhi3d6qlqluftw3ei
Generative Adversarial Learning for Reducing Manual Annotation in Semantic Segmentation on Large Scale Miscroscopy Images: Automated Vessel Segmentation in Retinal Fundus Image as Test Case
2017
2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The paper is aimed towards mitigating this labeling effort by leveraging the recent concept of generative adversarial network(GAN) wherein a generator maps latent noise space to realistic images while ...
Though our concept is generic, we applied it for the challenging task of vessel segmentation in fundus images. We show that proposed method is more data efficient than a CNN. ...
Both of these methods are further steps towards improving the performance of the combined DC-net. Figure 4 . 4 Exemplary real and generated image patches. ...
doi:10.1109/cvprw.2017.110
dblp:conf/cvpr/LahiriABM17
fatcat:fsuyir2hmfc63mi4oa25swdnfa
Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our approach, Adversarial Color Enhancement (ACE), generates unrestricted adversarial images by optimizing the color filter via gradient descent. ...
The future potential of filter-based adversaries is also explored in two directions: guiding ACE with common enhancement practices (e.g., Instagram filters) towards specific attractive image styles and ...
Acknowledgement This work was carried out on the Dutch national e-infrastructure with the support of SURF Cooperative. ...
arXiv:2002.01008v3
fatcat:6sssetbtura5zmyrrfos6ydooe
Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In Computer Vision, adversarial examples are images containing subtle perturbations generated by malicious optimization algorithms in order to fool classifiers. ...
Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving ...
help the community understand better the inner workings of deep learning models. ...
arXiv:2009.03728v1
fatcat:ysprss2tebcwrh4agv73v2mbpy
Experiential Robot Learning with Accelerated Neuroevolution
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The agents successfully navigate the given tasks, in a relatively low number of generations. Based on our results, we propose to use the algorithm in more complex tasks. ...
We test our algorithm first on a simulated task of playing the game Flappy Bird, then on a physical NAO robot in a static Object Centering task. ...
In effect, Deep Learning can generally be considered as gradient-based optimization of deep neural networks. ...
arXiv:1808.05525v1
fatcat:lvytoxr4hngtnck2h3q6jkf7w4
Rallying Adversarial Techniques against Deep Learning for Network Security
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2019 pre-print arXiv:1903.11688v1 fatcat:zk5kbymppzeodaj6ustnguwxsu
In this paper, we show that by modifying on average as little as 1.38 of the input features, an adversary can generate malicious inputs which effectively fool a deep learning based NIDS. ...
Recent advances in artificial intelligence and the increasing need for powerful defensive measures in the domain of network security, have led to the adoption of deep learning approaches for use in network ...
For example, one of the earliest adversarial example algorithms, Fast Gradient Sign Method (FGSM), perturbs every element of the input in the direction of its gradient by a fixed size [12] . ...
arXiv:1903.11688v2
fatcat:w4hosk6qh5aexmxducftuhxre4
Block-wise Image Transformation with Secret Key for Adversarially Robust Defense
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a novel defensive transformation that enables us to maintain a high classification accuracy under the use of both clean images and adversarial examples for adversarially robust ...
Overall, all three proposed algorithms are demonstrated to outperform state-of-the-art defenses including adversarial training whether or not a model is under attack. ...
They are helpful not only for evaluating the robustness of deep learning models but also for understanding them better. ...
arXiv:2010.00801v1
fatcat:qatibgapg5bhjipne6xpccqwfi
NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we propose a black-box adversarial attack algorithm that can defeat both vanilla DNNs and those generated by various defense techniques developed recently. ...
Instead of searching for an "optimal" adversarial example for a benign input to a targeted DNN, our algorithm finds a probability density distribution over a small region centered around the input, such ...
Acknowledgement: This work was supported in part by NSF-1836881, NSF-1741431, and ONR-N00014-18-1-2121. ...
arXiv:1905.00441v3
fatcat:ylbmyemfafgsnnth4r2fjnqgvq
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2019 pre-print arXiv:1903.10346v1 fatcat:hgzxyvzrhze3leffqx2vphfumm
In contrast, current targeted adversarial examples applied to speech recognition systems have neither of these properties: humans can easily identify the adversarial perturbations, and they are not effective ...
In this domain, adversarial examples can be constructed by imperceptibly modifying images to cause misclassification, and are practical in the physical world. ...
In particular, the adversary is allowed to compute gradients through the model in order to generate adversarial examples. ...
arXiv:1903.10346v2
fatcat:jcafk5wngfdabhd55wzds6bpjm
Towards Distributed Coevolutionary GANs
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Generative Adversarial Networks (GANs) have become one of the dominant methods for deep generative modeling. ...
Here, we investigate the use of coevolution, a class of black-box (gradient-free) co-optimization techniques and a powerful tool in evolutionary computing, as a supplement to gradient-based GAN training ...
The aim of this paper is to bridge the gap between works of the deep learning and evolutionary computing communities towards a better understanding of gradient-based and gradient-free GAN dynamics. ...
arXiv:1807.08194v3
fatcat:rygp4oljqjeb7npj3zxt4thkbu
Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This paper studies strategies to implement adversary robustly trained algorithms towards guaranteeing safety in machine learning algorithms. ...
We survey the most recent and important results in adversarial example generation, defense mechanisms with adversarial (re)Training as their main defense against perturbations. ...
This smoothness around training data points makes it difficult for exploiting algorithms to find meaningful directions towards the generation of an adversarial example. ...
arXiv:2007.00753v2
fatcat:6xjcd5kinzeevleev26jpj4mym
« Previous
Showing results 1 — 15 out of 3,459 results