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
APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
This dataset and the described experiments provide a benchmark for future research on the effectiveness of and defenses against physical adversarial objects in the wild. ...
Our results suggest that adversarial patches can be effectively flagged, both in a high-knowledge, attack-specific scenario, and in an unsupervised setting where patches are detected as anomalies in natural ...
We would also like to thank our MITRE colleagues who participated in collecting and annotating the APRICOT dataset and creating the adversarial patches. ...
arXiv:1912.08166v2
fatcat:b3uekiyoinf6zl2skwgbp2sgg4
ASC-Net: Unsupervised Medical Anomaly Segmentation Using an Adversarial-based Selective Cutting Network
[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.
This Adversarial-based Selective Cutting network (ASC-Net) bridges the two domains of cluster-based deep segmentation and adversarial-based anomaly/novelty detection algorithms. ...
In this paper we consider the problem of unsupervised anomaly segmentation in medical images, which has attracted increasing attention in recent years due to the expensive pixel-level annotations from ...
Unsupervised Anomaly Detection and Segmentation The primary school of thought in the case of unsupervised anomaly detection and segmentation has revolved around the idea of training frameworks to learn ...
arXiv:2112.09135v1
fatcat:gqnklo7kojbrlbz5navgn7slgq
ASC-Net : Adversarial-based Selective Network for Unsupervised Anomaly Segmentation
[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.
Other Versions
This Adversarial-based Selective Cutting network (ASC-Net) bridges the two domains of cluster-based deep learning methods and adversarial-based anomaly/novelty detection algorithms. ...
This concept tackles the task of unsupervised anomaly segmentation, which has attracted increasing attention in recent years due to their broad applications in tasks with unlabelled data. ...
Furthermore, under the constraints of the GAN discriminator and the reconstruction of the original input, our ASC-Net becomes an unsupervised solution for anomaly detection, since we do not have any labels ...
arXiv:2103.03664v2
fatcat:3mzltezwubfqfkqv5fkqzburam
Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
[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
Unsupervised learning of anomaly detection in high-dimensional data, such as images, is a challenging problem recently subject to intense research. ...
In this work, we evaluate the effects of anomaly contaminations in the training data on state-of-the-art GAN-based anomaly detection methods. As expected, detection performance deteriorates. ...
In the context of machine learning, anomaly detection can be supervised, semi-supervised, or unsupervised. This paper addresses unsupervised anomaly detection. ...
arXiv:1905.11034v2
fatcat:ghyb2wbiinbfvprc2nucbqlv5e
Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
[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.
Other Versions
Detecting out of distribution (OOD) samples is of paramount importance in all Machine Learning applications. ...
Our method outperforms the current state-of-the-art methods for anomaly detection on several OOD detection benchmarks. ...
This project was supported in part by NSF CAREER AWARD 1942230, an IBM faculty award, a grant from Capital One, and a Simons Fellowship on Deep Learning Foundations. ...
arXiv:2003.10713v3
fatcat:rhff735uxrborke4rwisjs6wm4
Effective Detection of Multimedia Protocol Tunneling using Machine Learning
2018
USENIX Security Symposium
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.
We also explore the application of semi-supervised and unsupervised machine learning techniques. ...
Our findings suggest that the existence of manually labeled samples is a requirement for the successful detection of covert channels. ...
Our work further explored the application of semi-supervised and unsupervised anomaly detection techniques in the same context. ...
dblp:conf/uss/Barradas0R18
fatcat:zcoll5ywurc43kobupk3spwphy
PORTFILER: Port-Level Network Profiling for Self-Propagating Malware Detection
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
PORTFILER extracts port-level features from the Zeek connection logs collected at a border of a monitored network, applies anomaly detection techniques to identify suspicious events, and ranks the alerts ...
It is challenging to detect these attacks in their early stages, as adversaries utilize common network services, use novel techniques, and can evade existing detection mechanisms. ...
ACKNOWLEDGEMENTS This research was sponsored by the contract number W911NF-18-C0019 with the U.S. ...
arXiv:2112.13798v2
fatcat:4exe4kpfdfhypjyxbkcv6iba5u
Anomaly Detection Using GANs for Visual Inspection in Noisy Training Data
[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
In recent years, due to the difficulty of defining anomalies and the limit of correcting their labels, research on unsupervised anomaly detection using generative models has attracted attention. ...
The detection and the quantification of anomalies in image data are critical tasks in industrial scenes such as detecting micro scratches on product. ...
In recent years, research on unsupervised anomaly detection using generative models has attracted attention. ...
arXiv:1807.01136v2
fatcat:plzffmummvbunpqjnh5mwpfqxu
A Decade of Social Bot Detection
[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
In this work, we briefly survey the first decade of research in social bot detection. ...
In the aftermath of the 2016 US elections, the world started to realize the gravity of widespread deception in social media. ...
social platforms -and the ability of humans in spotting bots in-the-wild. ...
arXiv:2007.03604v2
fatcat:6dilhijyzzgnhmlrl5ly2vknue
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking
[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
More importantly, we show that our approach produces state-of-the-art performance in several GAN-based applications -- anomaly detection, domain adaptation, and adversarial defense, that benefit from an ...
As a result, they have been widely adopted across a variety of applications, ranging from challenging inverse problems like image completion, to problems such as anomaly detection and adversarial defense ...
Anomaly Detection GANs have become a popular choice for unsupervised anomaly detection since out of distribution samples are represented as those samples with a relatively high reprojection error, since ...
arXiv:1912.07748v3
fatcat:danggesoinburbth2pixzj74pm
Semi-Supervised Anomaly Detection in Video-Surveillance Scenes in the Wild
2021
Sensors
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 anomaly detection in all of them. ...
In this work, it is proposed an approach for anomaly detection in video-surveillance scenes based on a weakly supervised learning algorithm. ...
Finally, in the context of unsupervised reconstruction-based models, also sparse combination learning techniques have been adopted in [12] to detect anomalies in surveillance contexts. ...
doi:10.3390/s21123993
pmid:34207883
pmcid:PMC8230050
fatcat:kvxd3ujt3rfohf5qg4s3eb4hzm
SIGL: Securing Software Installations Through Deep Graph 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.
Other Versions
and adversarial attack. ...
It can be used with application-specific models, even in the presence of new software versions, as well as application-agnostic meta-models that encompass a wide range of applications and installers. ...
The views, opinions, and/or findings contained in this paper are those of the authors and should not be interpreted as representing the official views or policies, either expressed or implied, of the sponsors ...
arXiv:2008.11533v2
fatcat:dqdb6itehjbhpesqq6pn56wasq
Deep Generative Models in the Industrial Internet of Things: A Survey
2022
IEEE Transactions on Industrial Informatics
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.
In this article, we review the state of the art of DGMs and their applicability to IIoT, classifying the reviewed works into the IIoT application areas of anomaly detection, trust-boundary protection, ...
Advances in communication technologies and artificial intelligence are accelerating the paradigm of industrial Internet of Things (IIoT). ...
databases and automatically learns the rapidly changing natures of unknown attack models by using unsupervised learning and unlabeled data from the wild. ...
doi:10.1109/tii.2022.3155656
fatcat:5np4ghh43nfqjkjycrzkle6vlu
A new interpretable unsupervised anomaly detection method based on residual explanation
2021
IEEE Access
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.
Although a current hot topic, further advances are still needed to overcome the existing limitations of the current interpretability methods in unsupervised DL-based models for Anomaly Detection (AD). ...
Despite the superior performance in modeling complex patterns to address challenging problems, the black-box nature of Deep Learning (DL) methods impose limitations to their application in real-world critical ...
ACKNOWLEDGMENTS The authors would like to thank VALE S.A. for the institutional support that made this work possible. ...
doi:10.1109/access.2021.3137633
fatcat:4ctyo2norbhahioqkuc2xj74je
Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification
[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
Anomaly detection algorithms find extensive use in various fields. This area of research has recently made great advances thanks to deep learning. ...
The method has shown promising results in both unsupervised and semi-supervised settings. ...
To detect new anomalies, many of these systems adopt an unsupervised learning approach as foundation for their detection algorithm. ...
arXiv:2001.08873v3
fatcat:bzxna4rtubb7pcv7qk24clfbji
« Previous
Showing results 1 — 15 out of 419 results