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.
Filters
Anomaly detection by using a combination of generative adversarial networks and convolutional autoencoders
2022
EURASIP Journal on Advances in Signal Processing
Preserved Fulltext
Generative adversarial networks (GANs) can simulate complex and high-dimensional distributions of data and can be used to learn the behavioral patterns of normal data for unsupervised anomaly detection ...
Thus, USADs (an unsupervised anomaly detection model) utilize an autoencoder (AE) to undertake the task of the generator and discriminator and enhance the stability during adversarial training by using ...
The adversarial generative architecture was then used to learn the high-dimensional distribution of the normal data. ...
doi:10.1186/s13634-022-00943-7
fatcat:62qlwlxlf5holgnup2gx6ots7m
IoT Network Traffic Analysis with Deep Learning
[article]
2024
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 2024; you can also visit the original URL.
The file type is application/pdf.
As IoT networks become more complex and generate massive amounts of dynamic data, it is difficult to monitor and detect anomalies using traditional statistical methods and machine learning methods. ...
Deep learning algorithms can process and learn from large amounts of data and can also be trained using unsupervised learning techniques, meaning they don't require labelled data to detect anomalies. ...
They can also be used for unsupervised AD tasks, and be adapted to different types of data, as they can be trained on a variety of data distributions, including high-dimensional and sparse data. ...
arXiv:2402.04469v1
fatcat:mdeohwmfuzgpjaxxq4tz5ljy5i
Adversarial Attacks and Defense in Deep Reinforcement Learning (DRL)-Based Traffic Signal Controllers
2021
IEEE Open Journal of Intelligent Transportation Systems
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.
The results of anomaly detectors indicates that low-cost ensemble model achieves the best anomaly detection performance in all attack models and DRL settings. ...
In this paper, first, we explore the security vulnerabilities of DRL-based TSCs in the presence of adversarial attacks. ...
PCA-based Summary Statistic High dimensional observation may exhibit sparse data structure so the underlying independent data dimension can be lower than the actual data dimension. ...
doi:10.1109/ojits.2021.3118972
fatcat:fbtbpwn4yrgh3k2yzxqvorq3qq
WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
[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:1810.01392v3 fatcat:kw6llwmzdvba7anqs6a2m55briOther Versions
One proposal to scale OoD detection to high-dimensional data is to learn a tractable likelihood approximation of the training distribution, and use it to reject unlikely inputs. ...
To mitigate this problem, we propose Generative Ensembles, which robustify density-based OoD detection by way of estimating epistemic uncertainty of the likelihood model. ...
Generative Ensembles of GANs We describe how to improve GAN-based anomaly detection with ensembles. ...
arXiv:1810.01392v4
fatcat:pokpwiujwzakhfqlu4aiueksry
Hybrid Deep Learning Model using SPCAGAN Augmentation for Insider Threat Analysis
[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.
We propose a linear manifold learning-based generative adversarial network, SPCAGAN, that takes input from heterogeneous data sources and adds a novel loss function to train the generator to produce high-quality ...
Anomaly detection using deep learning requires comprehensive data, but insider threat data is not readily available due to confidentiality concerns of organizations. ...
In this paper, we combine the potential of Generative Adversarial Networks(GANs) [7] to perform data augmentation and hybrid model using Bayesian Neural Networks(BNNs) for improved anomaly detection. ...
arXiv:2203.02855v1
fatcat:naeat2lz4jg65bp2gaw2tzp25q
Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic 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.
network instead of just its output, generating training data for the OOD detector by leveraging blind spots in the segmentation network and focusing the generated data on localized regions in the image ...
Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA). ...
in the multi-million dimensional parameter space of the network. ...
arXiv:2108.01634v1
fatcat:qeaiycs47rbaddadl7z3yrhdc4
Detecting malicious logins as graph anomalies
[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
We test this technique with a small cohort of privileged accounts using real login data from an operational enterprise network. ...
We find that the method is generally successful at detecting a broad range of lateral movement for each user, with false positive rates significantly lower than those resulting from alerts based solely ...
Acknowledgement The author acknowledges use of the GBAD software from https://users.csc.tntech.edu/~weberle/gbad/.
References ...
arXiv:1909.09047v2
fatcat:u57kbqlswvhszgix4t3542esni
Diverse Counterfactual Explanations for Anomaly Detection in Time Series
[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.
Moreover, we design a sparse variant of our method to improve the interpretability of counterfactual explanations for high-dimensional time series anomalies. ...
We investigate the value of our method on univariate and multivariate real-world datasets and two deep-learning-based anomaly detection models, under several explainability criteria previously proposed ...
Sparse counterfactual explanations for high-dimensional time series In high-dimensional settings (typically D > 10), restricting the perturbations to act on short temporal windows (less than 10 timestamps ...
arXiv:2203.11103v1
fatcat:odumbeqcsvculm6jdakpyft6ei
A Survey of Deep Learning Solutions for Anomaly Detection in Surveillance Videos
2021
International Journal of Computer and Information Technology(2279-0764)
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.
Hence, it has been widely applied to solve complex cognitive tasks like the detection of anomalies in surveillance videos. ...
This review attempts to provide holistic benchmarking of the published deep learning solutions for videos anomaly detection since 2016. ...
Vu and others [34] is another case of ensemble learning that combines Conditional Generative Adversarial Networks, R-CNN and Support Vector Machines (SVM).
D. ...
doi:10.24203/ijcit.v10i5.166
fatcat:kbqkwer2nvh5jk6gv54xygiueq
Unsupervised Abnormality Detection Using Heterogeneous Autonomous Systems
[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
Also, an autonomous vehicle provides various data types like images and other analog or digital sensor data, all of which can be useful in anomaly detection if leveraged fruitfully. ...
Anomaly detection (AD) in a surveillance scenario is an emerging and challenging field of research. ...
In this paper, means of cross-modal Generative Adversarial Network (GAN) is used for processing high dimensional visual data. Baydoun et al. ...
arXiv:2006.03733v2
fatcat:g3nn4pavijcwjdrkuiwxu7pksa
Anomaly Detection with Ensemble of Encoder and Decoder
[article]
2023
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 2023; you can also visit the original URL.
The file type is application/pdf.
In this work, we propose a novel anomaly detection method by modeling the data distribution of normal samples via multiple encoders and decoders. ...
Training samples are re-weighted to focus more on missed correlations between features of normal data. ...
GAN consists of a generator and a discriminator, capable of learning complex and high-dimensional data distribution via adversarial training. ...
arXiv:2303.06431v1
fatcat:m5rjwgcxbvcofb5xty763c7y6q
Tiki-Taka
2020
Proceedings of the 2020 ACM SIGSAC Conference on Cloud Computing Security Workshop
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.
Neural networks are increasingly important in the development of Network Intrusion Detection Systems (NIDS), as they have the potential to achieve high detection accuracy while requiring limited feature ...
To counteract these weaknesses, we propose three defense mechanisms, namely: model voting ensembling, ensembling adversarial training, and query detection. ...
Is there any "Achilles' heel" that can be exploited to compromise the expected high detection accuracy of neural network-based NID models? ...
doi:10.1145/3411495.3421359
fatcat:ispgcjohqvh6ji6faarl3vpkky
Adversarial Machine Learning Attacks and Defenses in Network Intrusion Detection Systems
2022
International Journal of Wireless and Microwave Technologies
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 focus on the evasion attacks against Network Intrusion Detection System (NIDS) and specifically on designing novel adversarial attacks and defenses using adversarial training. ...
We propose white box attacks against intrusion detection systems. Under these attacks, the detection accuracy of model suffered significantly. ...
To address the issue of high dimensionality Liu et al. [16] proposed the use of Sparse Auto Encoder for compressing the traffic flows and classification using Random Forest. ...
doi:10.5815/ijwmt.2022.01.02
fatcat:v76pnse6zjbwxe35wc7lfumhna
IBaggedFCNet: An Ensemble Framework for Anomaly Detection in Surveillance Videos
2020
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 2020; you can also visit the original URL.
The file type is application/pdf.
This is due to the fact ensemble learning increases generalization of the base classifier and reduces variance, thereby performing well on unseen test data. ...
CNN based LSTM with its ability to learn sequential data, that is crucial for encoding temporal information in videos, is used in Autoencoders and Generative Adversarial Networks (GAN) as well as independently ...
doi:10.1109/access.2020.3042222
fatcat:ebflecvnszfr5beyy6q5xb2kxa
A Survey on Explainable Anomaly Detection
[article]
2023
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 2023; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In the past two decades, most research on anomaly detection has focused on improving the accuracy of the detection, while largely ignoring the explainability of the corresponding methods and thus leaving ...
We propose a taxonomy based on the main aspects that characterize each explainable anomaly detection technique, aiming to help practitioners and researchers find the explainable anomaly detection method ...
ACKNOWLEDGMENTS This publication is part of the project Digital Twin with project number P18-03 of the research programme TTW Perspective, which is (partly) financed by the Dutch Research Council (NWO) ...
arXiv:2210.06959v2
fatcat:gggheaoiw5ds5kn3eepa2gu3wa
« Previous
Showing results 1 — 15 out of 1,276 results