Intrusion Detection for Ubiquitous &amp; Pervasive Environments using Plan Recognition

Walker, Jessie; Jones, Travis L.; Blount, Roy; Aydın, Kemal

doi:10.5383/juspn.03.01.001

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we implemented a distributed regression-based algorithm called iterative shrinkage-thresholding algorithm (DISTA), a stochastic optimization algorithm that can handle a large amount of training instances. Our experiments in [21] showed that it can improve model accuracy by up to 16% by incorporating our feature selection strategy compared to other baselines.…”

Section: Sentiment Analysis Model and Algorithmsmentioning

confidence: 87%

“…The authors of [21] contend that secondary components, such as alarm systems, RFIDs, and navigation systems, tend to be more vulnerable than traditional computers and therefore are likely points of attack. They further propose a defensive plan recognition model that can predict likely actions and advise a system to either aid or hamper an observed agent by suggesting or forcing particular actions.…”

Section: Mapping Attacksmentioning

confidence: 99%

“…We are training a predictive model which combines the algorithms presented here and in [21] to classify the sentiment of a sentence. This predictive model has three basic features: first, the integer value generated from our compositional semantic rules; second, the float value of the phrase scoring algorithm; and, third, the output of the polaritychecking algorithm.…”

Section: Special Casesmentioning

confidence: 99%

See 2 more Smart Citations

Ontology-Driven Cyber-Security Threat Assessment Based on Sentiment Analysis of Network Activity Data

Lundquist

Zhang

Ouksel

2014

2014 International Conference on Cloud and Autonomic Computing

View full text Add to dashboard Cite

Sentiment analysis is gaining acceptance as a tool for automated understanding of consumer attitudes and preferences. Based on well-designed rule sets that describe how most people express their sentiments, sentiment analysis models enable automated processes to understand human responses. In this paper, we describe our vision of extending sentiment analysis to the novel domain of cyber-security. Our proposal combines: 1) ontological modeling of attacks, defenses, and attacker goals; 2) sentiment analysis of combinations of elements indicative of probable attacks; and 3) semantic reconciliation of borderline cases to more definitively classify ambiguous network activity as threatening or innocuous. This method has achieved good results (86% correct) in assessing consumer sentiments, and we believe that more detailed models can improve on this accuracy even in the complex domain of cyber-security.

show abstract

Section: Sentiment Analysis Model and Algorithmsmentioning

confidence: 87%

Section: Mapping Attacksmentioning

confidence: 99%

Section: Special Casesmentioning

confidence: 99%

See 1 more Smart Citation