11,950 Hits in 5.8 sec

Machine learning for intrusion detection in industrial control systems: challenges and lessons from experimental evaluation

Gauthama Raman M. R., Chuadhry Mujeeb Ahmed, Aditya Mathur
2021 Cybersecurity  
Towards this end, a class of anomaly detectors, created using data-centric approaches, are gaining attention.  ...  The use of these approaches leads to relatively easier and faster creation of anomaly detectors compared to the use of design-centric approaches that are based on plant physics and design.  ...  Lessons learned: 1 Anomaly detectors should be capable of updating their reference model at regular intervals through online learning. 2 There should be an automated mechanism that initiates the retraining  ... 
doi:10.1186/s42400-021-00095-5 fatcat:fr4h45z5zzhsfod4z663iildl4

Towards ground truthing observations in gray-box anomaly detection

Jiang Ming, Haibin Zhang, Debin Gao
2011 2011 5th International Conference on Network and System Security  
We implement a host-based anomaly detector with our proposed taint tracking and evaluate the accuracy of rules learned.  ...  A gray-box anomaly detector first observes benign executions of a computer program and then extracts reliable rules that govern the normal execution of the program.  ...  Peng et al. has more detailed descriptions on the various relations that can be learned in their proposed anomaly detector [13] .  ... 
doi:10.1109/icnss.2011.6059956 dblp:conf/nss/MingZG11 fatcat:26bhyulppvcmzdfkgnnfryvhfu

Towards Deep Industrial Transfer Learning for Anomaly Detection on Time Series Data [article]

Benjamin Maschler, Tim Knodel, Michael Weyrich
2021 arXiv   pre-print
In this article, a modular deep learning algorithm for anomaly detection on time series datasets is presented that allows for an easy integration of such transfer learning capabilities.  ...  It is thoroughly tested on a dataset from a discrete manufacturing process in order to prove its fundamental adequacy towards deep industrial transfer learning - the transfer of knowledge in industrial  ...  Comparison with Conventional Deep Learning Anomaly Detector For a final evaluation of the modular deep-learning-based anomaly detection algorithm, a comparison with a conventional deep-learning-based anomaly  ... 
arXiv:2106.04920v1 fatcat:bth6dzh6h5cs7getlfihqvq7ui

Anomaly Detection in Gravitational Waves data using Convolutional AutoEncoders [article]

Filip Morawski, Michał Bejger, Elena Cuoco, Luigia Petre
2021 arXiv   pre-print
The anomalies we study are transient signals, different from the slow non-stationary noise of the detector.  ...  In this paper, we propose an alternative generic method of studying GW data based on detecting anomalies.  ...  Essentially, the AE learns a vector field for mapping input data towards lower dimensional manifolds, that describe the high density region where input data concentrates.  ... 
arXiv:2103.07688v1 fatcat:cmvhsopokngshhtqlcaco7ceoi

A lightweight snapshot-based DDoS detector

Gilles Roudiere, Philippe Owezarski
2017 2017 13th International Conference on Network and Service Management (CNSM)  
In this paper we introduce AATAC (Autonomous Algorithm for Traffic Anomaly Detection), an unsupervised DDoS detector that focuses on reducing the computational resources needed to process the traffic.  ...  Thus, setting up, configuring and keeping up to date an anomaly detector should be an easy task.  ...  Supervised machine learning autonomously learn the traffic characteristics using a hand-crafted labelled dataset, then detect deviation toward the produced model while in operation.  ... 
doi:10.23919/cnsm.2017.8256014 dblp:conf/cnsm/RoudiereO17 fatcat:qboo4l4pwre5njgbaonsvq7wqq

An Autonomous Self-Incremental Learning Approach for Detection of Cyber Attacks on Unmanned Aerial Vehicles (UAVs) [article]

Yasir Ali Farrukh, Irfan Khan
2021 arXiv   pre-print
In our approach, we have combined signature-based detection along with anomaly detection in such a way that the signature-based detector autonomously updates its attack classes with the help of an anomaly  ...  Moreover, our anomaly-based detector has achieved a 100% detection rate for attacks.  ...  is now shifting towards autonomous and digitalized as an anomaly[6].  ... 
arXiv:2112.11219v1 fatcat:sm2l5mko7fahjkxiyztl3ybrem

Consensus extraction from heterogeneous detectors to improve performance over network traffic anomaly detection

Jing Gao, Wei Fan, Deepak Turaga, Olivier Verscheure, Xiaoqiao Meng, Lu Su, Jiawei Han
2011 2011 Proceedings IEEE INFOCOM  
Through experimental results on three network anomaly detection datasets, we show that the combined detector improves over the base detectors by 10% to 20% in accuracy.  ...  In contrast, the combination of multiple atomic detectors can provide a more powerful anomaly capturing capability when the base detectors complement each other.  ...  Many studies in ensemble learning have shown that the diversity among base detectors can greatly improve the combination performance [5, 6] .  ... 
doi:10.1109/infcom.2011.5934982 dblp:conf/infocom/GaoFTVMSH11 fatcat:vscwk4b2yfdd7cag7hoyrvt55e

An Immunology Inspired Flow Control Attack Detection Using Negative Selection with R-Contiguous Bit Matching for Wireless Sensor Networks

Muhammad Zeeshan, Huma Javed, Amna Haider, Aumbareen Khan
2015 International Journal of Distributed Sensor Networks  
This paper implemented an improved, decentralized, and customized version of the Negative Selection Algorithm (NSA) for data flow anomaly detection with learning capability.  ...  An Anomaly Detection System (ADS) framework inspired from the Human Immune System is implemented in this paper for detecting Sybil attacks in WSNs.  ...  Conflict of Interests The authors declare that there is no conflict of interests regarding the publication of this paper.  ... 
doi:10.1155/2015/169654 fatcat:pkfqehjq6fgv3hqevsxpvhjiva

Finite Sample Complexity of Rare Pattern Anomaly Detection

Md Amran Siddiqui, Alan Fern, Thomas G. Dietterich, Shubhomoy Das
2016 Conference on Uncertainty in Artificial Intelligence  
Finally, we design a new simple anomaly detection algorithm motivated by our analysis and show experimentally on several benchmark problems that it is competitive with a state-of-the-art detector using  ...  However, compared to supervised learning, there has been very little work aimed at understanding the sample complexity of anomaly detection.  ...  The primary goal of this paper is to move toward an understanding of these empirical observations by analyzing the sample complexity of a certain class of anomaly detectors.  ... 
dblp:conf/uai/SiddiquiFDD16 fatcat:d2ikhytdgvbijfqtvt6qeeeyuu


Dapeng Liu, Youjian Zhao, Haowen Xu, Yongqian Sun, Dan Pei, Jiao Luo, Xiaowei Jing, Mei Feng
2015 Proceedings of the 2015 ACM Conference on Internet Measurement Conference - IMC '15  
Multiple existing detectors are applied to the performance data in parallel to extract anomaly features.  ...  However, even though dozens of anomaly detectors have been proposed over the years, deploying them to a given service remains a great challenge, requiring manually and iteratively tuning detector parameters  ...  We also thank Jun Zhu for his knowledge of machine learning, and Kaixin Sui for her suggestion on the detection framework.  ... 
doi:10.1145/2815675.2815679 dblp:conf/imc/LiuZXSPLJF15 fatcat:5b7m523va5ezrmwuztp2fbqjna

Active Anomaly Detection via Ensembles: Insights, Algorithms, and Interpretability [article]

Shubhomoy Das, Md Rakibul Islam, Nitthilan Kannappan Jayakodi, Janardhan Rao Doppa
2019 arXiv   pre-print
In this paper, we study the problem of active learning to automatically tune ensemble of anomaly detectors to maximize the number of true anomalies discovered.  ...  We make four main contributions towards this goal.  ...  This feedback is used by the anomaly detector to change the scoring mechanism of data instances towards the goal of increasing the true anomalies appearing at the top of the ranked list.  ... 
arXiv:1901.08930v1 fatcat:c7fzvvm6e5cgnmknq56tobpgiq

Online Self-Evolving Anomaly Detection in Cloud Computing Environments [article]

Haili Wang, Jingda Guo, Xu Ma, Song Fu, Qing Yang, Yunzhong Xu
2021 arXiv   pre-print
Our framework self-evolves by recursively exploring newly verified anomaly records and continuously updating the anomaly detector online.  ...  Moreover, we design two types of detectors, one for general anomaly detection and the other for type-specific anomaly detection.  ...  These detectors are homogeneous that simultaneously detect anomaly, learn model incrementally and select the most discriminatory attributes.  ... 
arXiv:2111.08232v1 fatcat:u43drqxuvfek7mcalzrksql3im

Siamese Neural Networks for One-shot detection of Railway Track Switches [article]

Dattaraj J Rao, Shruti Mittal, S. Ritika
2017 arXiv   pre-print
Switch will be one of those images that will be different and we will find a mapping that clearly distinguishes the Switch from other possible Track anomalies.  ...  Modern trains use high definition video cameras facing the Track that continuously record video from track.  ...  This concept is used to develop One-Shot Detector models that can learn on limited examples.  ... 
arXiv:1712.08036v1 fatcat:hirrbhqeuzaxxgaeybelyc24py

Time Series Anomaly Detection for Smart Grids: A Survey [article]

Jiuqi Zhang, Di Wu, Benoit Boulet
2021 arXiv   pre-print
Specifically, we first outline current research challenges in the power grid anomaly detection domain and further review the major anomaly detection approaches.  ...  Various methods have been proposed for anomaly detection on power grid time-series data.  ...  In conclusion, we believe that anomaly detection would continue to play a crucial role in the future quest for the reliability and operational efficiency of power grids.  ... 
arXiv:2107.08835v1 fatcat:boxplqijengbhhzi5jz23t54fe

Hybrid data-driven physics model-based framework for enhanced cyber-physical smart grid security

Cody Ruben, Surya Chandan Dhulipala, Keerthiraj Nagaraj, Sheng Zou, Allen Starke, Arturo Bretas, Alina Zare, Janise McNair
2019 IET Smart Grid  
Multiple anomaly detection methods working at both the system level and distributed local detection level are fused.  ...  The fusion takes into consideration the confidence of the various anomaly detection methods to provide the best overall detection results.  ...  The contributions of this paper towards the state-of-the-art are as follows: • Decision level fusion is used to create a hybrid physics-based data-driven anomaly detection that considers the confidence  ... 
doi:10.1049/iet-stg.2019.0272 fatcat:i5t2emtmt5h7xgbr7oic5u5pge
« Previous Showing results 1 — 15 out of 11,950 results