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
Deep Neural Rejection against Adversarial Examples
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
In this work, we propose a deep neural rejection mechanism to detect adversarial examples, based on the idea of rejecting samples that exhibit anomalous feature representations at different network layers ...
Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples that are carefully perturbed ...
ATTACKING DEEP NEURAL REJECTION To properly evaluate security, or adversarial robustness, of rejection-based defenses against adaptive white-box adversarial examples, we propose the following. ...
arXiv:1910.00470v3
fatcat:dzpgmactbvhhlphvifqpnxsqbu
Deep neural rejection against adversarial examples
2020
EURASIP Journal on Information Security
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 work, we propose a deep neural rejection mechanism to detect adversarial examples, based on the idea of rejecting samples that exhibit anomalous feature representations at different network layers ...
Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples that are carefully perturbed ...
Attacking deep neural rejection To properly evaluate security, or adversarial robustness, of rejection-based defenses against adaptive white-box adversarial examples, we propose the following. ...
doi:10.1186/s13635-020-00105-y
fatcat:grtxarwetnesbkvd57kuncypou
A Survey on Adversarial Examples in Deep Learning
2020
Journal on Big Data
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 2022; you can also visit the original URL.
The file type is application/pdf.
Adversarial examples are hot topics in the field of security in deep learning. ...
This article explains the key technologies and theories of adversarial examples from the concept of adversarial examples, the occurrences of the adversarial examples, the attacking methods of adversarial ...
Papernot proposed a distillation defense mechanism against adversarial examples for deep neural networks, and verified the effectiveness of their defense mechanisms on two types of deep neural networks ...
doi:10.32604/jbd.2020.012294
fatcat:2o5bsbqyurfj7igqyqbs47fjre
Hack The Box: Fooling Deep Learning Abstraction-Based Monitors
[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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2107.04764v2 fatcat:pn3aio477vdynn6uof5wy2jqmiOther Versions
In this paper, we consider the case study of abstraction-based novelty detection and show that it is not robust against adversarial samples. ...
Moreover, we show the feasibility of crafting adversarial samples that fool the deep learning classifier and bypass the novelty detection monitoring at the same time. ...
Adversarial attacks against neural networks Another idea is to use known adversarial attacks against neural networks as a starting point for attacking the monitor. ...
arXiv:2107.04764v3
fatcat:sgojuv5bhja6zfjmarl5hprdf4
Detecting Black-box Adversarial Examples through Nonlinear Dimensionality Reduction
2019
The European Symposium on Artificial Neural Networks
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.
Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. ...
Our empirical findings show that the proposed approach is able to effectively detect adversarial examples crafted by non-adaptive attackers, i.e., not specifically tuned to bypass the detection method. ...
Introduction Deep neural networks (DNNs) reach state-of-the-art performances in a wide variety of pattern recognition tasks. ...
dblp:conf/esann/CrecchiBB19
fatcat:vvzw2avibrcnvh2pemcsrzhqhe
Integration of statistical detector and Gaussian noise injection detector for adversarial example detection in deep neural networks
2019
Multimedia tools and applications
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.
Existing deep learning-based adversarial detection methods require numerous adversarial images for their training. ...
In particular, the Gaussian process regression-based detector shows better detection performance than the baseline models for most attacks in the case with fewer adversarial examples. ...
From the perspective of a system with a deep learning model, it is possible to further secure the system by rejecting the adversarial example input, after determining through adversarial detection whether ...
doi:10.1007/s11042-019-7353-6
fatcat:3jlzbd37pzcvneuyis7ai3vkki
Are Generative Classifiers More Robust to Adversarial Attacks?
[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:
2018 pre-print arXiv:1802.06552v2 fatcat:3pjifn3h4fcfle7oqd3dbifkliOther Versions
We further develop detection methods for adversarial examples, which reject inputs with low likelihood under the generative model. ...
There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. ...
Introduction Deep neural networks have been shown to be vulnerable to adversarial examples (Szegedy et al., 2013; Goodfellow et al., 2014) . ...
arXiv:1802.06552v3
fatcat:tyjy55zu7bfkvexaj5vh6u2diq
FADER: Fast Adversarial Example Rejection
[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.
Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. ...
FADER overcome the issues above by employing RBF networks as detectors: by fixing the number of required prototypes, the runtime complexity of adversarial examples detectors can be controlled. ...
Deep Neural Reject Sotgiu et al. ...
arXiv:2010.09119v1
fatcat:ffotkbvncngkdf6pp4gixhraii
ATRO: Adversarial Training with a Rejection Option
[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.
To this end, various methods are proposed to obtain a classifier that is robust against adversarial examples. ...
In this paper, in order to acquire a more reliable classifier against adversarial attacks, we propose the method of Adversarial Training with a Rejection Option (ATRO). ...
Benchmark Test using Neural Networks We compare the ATRO using a deep linear SVM with a plain deep linear SVM with a rejection option without adversarial training. ...
arXiv:2010.12905v1
fatcat:6jydra4ssjdr3jo6wqb6knjrea
Detecting Adversarial Examples through Nonlinear Dimensionality Reduction
[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.
Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. ...
Our empirical findings show that the proposed approach is able to effectively detect adversarial examples crafted by non-adaptive attackers, i.e., not specifically tuned to bypass the detection method. ...
Introduction Deep neural networks (DNNs) reach state-of-the-art performances in a wide variety of pattern recognition tasks. ...
arXiv:1904.13094v2
fatcat:hd7bpc6fxzfjpan24f5nh2537q
Is Deep Learning Safe for Robot Vision? Adversarial Examples Against the iCub Humanoid
2017
2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
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.
Deep neural networks have been widely adopted in recent years, exhibiting impressive performances in several application domains. ...
It has however been shown that they can be fooled by adversarial examples, i.e., images altered by a barely-perceivable adversarial noise, carefully crafted to mislead classification. ...
Despite its impressive performances, recent work has shown how deep neural networks can be fooled by well-crafted adversarial examples affected by a barely-perceivable adversarial noise. ...
doi:10.1109/iccvw.2017.94
dblp:conf/iccvw/MelisDB0FR17
fatcat:nzcm4nqh5rep5cuilwcvjd7req
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid
[article]
2017
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.
Deep neural networks have been widely adopted in recent years, exhibiting impressive performances in several application domains. ...
In this work, we aim to evaluate the extent to which robot-vision systems embodying deep-learning algorithms are vulnerable to adversarial examples, and propose a computationally efficient countermeasure ...
Security Evaluation against Adversarial Examples. We now investigate the security of iCub in the presence of adversarial examples. ...
arXiv:1708.06939v1
fatcat:xhzbo7mfjffsbhe7m7z4bk6dsq
Nearest neighbor pattern classification
1967
IEEE Transactions on Information Theory
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.
We further develop detection methods for adversarial examples, which reject inputs with low likelihood under the generative model. ...
There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. ...
INTRODUCTION Deep neural networks have been shown to be vulnerable to adversarial examples (Szegedy et al., 2013; Goodfellow et al., 2014) . ...
doi:10.1109/tit.1967.1053964
fatcat:wwzmy2yd3nb4znbhe7mno7w2bi
Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning
[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.
Other Versions
Detection and rejection of adversarial examples in security sensitive and safety-critical systems using deep CNNs is essential. ...
In this paper, we propose an approach to augment CNNs with out-distribution learning in order to reduce misclassification rate by rejecting adversarial examples. ...
PROPOSED METHOD It has been argued that a central element explaining the success of deep neural networks is their capacity to learn distributed representations [2] . ...
arXiv:1804.08794v2
fatcat:fytfdlk26jd6paq453of7stmgy
Robust Deep Neural Networks Inspired by Fuzzy Logic
[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
Through experiments on MNIST and CIFAR-10, the new models are shown to be more local, better at rejecting noise samples, and more robust against adversarial examples. ...
Deep neural networks have achieved impressive performance and become the de-facto standard in many tasks. ...
Preliminary results show that the proposed models are more well-behaving on noise patterns and more robust against adversarial examples. ...
arXiv:1911.08635v3
fatcat:qjkpmpdfbnaqzbwmz3s76pxu7i
« Previous
Showing results 1 — 15 out of 4,767 results