Deep Learning Based Forecasting of Critical Infrastructure Data

Zohrevand, Zahra; Glässer, Uwe; Tayebi, Mohammad A.; Shahir, Hamed Yaghoubi; Shirmaleki, Mehdi; Shahir, Amir Yaghoubi

doi:10.1145/3132847.3133031

Cited by 10 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep neural networks (DNNs) perform exceptionally well on many machine learning tasks, including safety-and security-sensitive applications such as self-driving cars [5], malware classification [48], face recognition [47], and critical infrastructure [71]. Robustness against malicious behavior is important in many of these applications, yet in recent years it has become clear that DNNs are vulnerable to a broad range of attacks.…”

Section: Introductionmentioning

confidence: 99%

Certified Robustness to Adversarial Examples with Differential Privacy

Lécuyer

Atlidakis

Geambasu

et al. 2019

2019 IEEE Symposium on Security and Privacy (SP)

568

537

View full text Add to dashboard Cite

Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed in a tight back-and-forth. Most past defenses are best effort and have been shown to be vulnerable to sophisticated attacks. Recently a set of certified defenses have been introduced, which provide guarantees of robustness to normbounded attacks. However these defenses either do not scale to large datasets or are limited in the types of models they can support. This paper presents the first certified defense that both scales to large networks and datasets (such as Google's Inception network for ImageNet) and applies broadly to arbitrary model types. Our defense, called PixelDP, is based on a novel connection between robustness against adversarial examples and differential privacy, a cryptographically-inspired privacy formalism, that provides a rigorous, generic, and flexible foundation for defense.

show abstract

Section: Introductionmentioning

confidence: 99%

Certified Robustness to Adversarial Examples with Differential Privacy

Lécuyer

Atlidakis

Geambasu

et al. 2019

2019 IEEE Symposium on Security and Privacy (SP)

568

537

View full text Add to dashboard Cite

show abstract

“…Also, the Receiver Operating Characteristic (ROC) curve is used to manage tradeoffs between F P and T P. Meanwhile, methods are often compared with baseline methods to examine the improvement. Some error-based metrics are also applied to measure the prediction and reconstruction performance such as Mean Absolute Error (MAE) and Relative Errors (ReErr) [117].…”

Section: Implementation and Evaluation Metricsmentioning

confidence: 99%

“…However, to increase the accuracy, these two kinds of methods can be placed parallelly to learn the characteristics of input data. Zohrevand et al [117] proposed a framework named MBPF that ensembles two components: (1) a statistical method named TBATS (Trigonometric Box-Cox transform, ARMA errors, Trend, and Seasonal components) [22], and (2) Multi-branch Deep Network Component. First, seasonality evaluation and outlier elimination are applied to remove noise.…”

Section: Representative New Techniquesmentioning

confidence: 99%

Deep Learning-Based Anomaly Detection in Cyber-Physical Systems: Progress and Opportunities

Luo,

Xiao,

Cheng

et al. 2020

Preprint

View full text Add to dashboard Cite

Anomaly detection is crucial to ensure the security of cyber-physical systems (CPS). However, due to the increasing complexity of CPSs and more sophisticated attacks, conventional anomaly detection methods cannot be directly applied to thwart such issues, which also need domain-specific knowledge and handle the growing volume of data. Deep learning-based anomaly detection (DLAD) methods have been proposed to achieve unsupervised detection in the era of CPS big data. In this paper, we review state-of-the-art DLAD methods in CPSs. We propose a taxonomy in terms of the type of anomalies, strategies, implementation and evaluation metrics to understand the essential properties of current methods. Further, we utilize this taxonomy to identify and highlight new characteristics and designs in each CPS domain. We summarise a list of publicly available datasets for training and evaluation. We also discuss our findings, the limitations of existing studies, and possible directions to improve DLAD methods.CCS Concepts: • Security and privacy → Intrusion/anomaly detection and malware mitigation; • Computer systems organization → Embedded and cyber-physical systems.

show abstract

“…These kinds of methods, perform an early prediction and readjust their result by benefitting from contextual information. For example, [96] proposes a deep learning based framework for time series analysis and prediction by ensembling parametric (TBATS) and non-parametric (deep network) methods. This study applies time-based generated features as contextual information to balance the obtained predicted values from two different methods.…”

Section: Causal Relation Based Correlationmentioning

confidence: 99%

“…Many of them have considered Neural Networks or deep learning as suitable candidates for data-driven model. For example [39,20,96] apply combination of ANN and ARIMA for TS, water quality and photo-voltaic power generators forecasting, time series forecasting, respectively. Another approach toward taking advantage of combination of models in ADS context is deep hybrid models, which is based on two step learning models.…”

Section: Advanced Data Driven Modelsmentioning

confidence: 99%

Should I Raise The Red Flag? A comprehensive survey of anomaly scoring methods toward mitigating false alarms

Zohrevand,

Glässer

2019

Preprint

Self Cite

View full text Add to dashboard Cite

A general Intrusion Detection System (IDS) fundamentally acts based on an Anomaly Detection System (ADS) or a combination of anomaly detection and signature-based methods, gathering and analyzing observations and reporting possible suspicious cases to a system administrator or the other users for further investigation. One of the notorious challenges which even the state-of-the-art ADS and IDS have not overcome is the possibility of a very high false alarms rate. Especially in very large and complex system settings, the amount of low-level alarms easily overwhelms administrators and increases their tendency to ignore alerts. We can group the existing false alarm mitigation strategies into two main families: The first group covers the methods directly customized and applied toward higher quality anomaly scoring in ADS. The second group includes approaches utilized in the related contexts as a filtering method toward decreasing the possibility of false alarm rates. Given the lack of a comprehensive study regarding possible ways to mitigate the false alarm rates, in this paper, we review the existing techniques for false alarm mitigation in ADS and present the pros and cons of each technique. We also study a few promising techniques applied in the signature-based IDS and other related contexts like commercial Security Information and Event Management (SIEM) tools, which are applicable and promising in the ADS context. Finally, we conclude with some directions for future research.

show abstract

Deep Learning Based Forecasting of Critical Infrastructure Data

Cited by 10 publications

References 13 publications

Certified Robustness to Adversarial Examples with Differential Privacy

Certified Robustness to Adversarial Examples with Differential Privacy

Deep Learning-Based Anomaly Detection in Cyber-Physical Systems: Progress and Opportunities

Should I Raise The Red Flag? A comprehensive survey of anomaly scoring methods toward mitigating false alarms

Contact Info

Product

Resources

About