Application of Deep Recurrent Neural Networks for Prediction of User Behavior in Tor Networks

Ishitaki, Taro; Obukata, Ryoichiro; Oda, Tetsuya; Barolli, Leonard

doi:10.1109/waina.2017.63

Cited by 22 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This scenario can only occur when robustness label(x i ) < robustness label(x j ). However; since, the training set is sufficiently large, and LSTM tends to provide substantial prediction accuracy, when trained by sufficiently large training set [21], the chances of the event-[robustness label(x i ) < robustness label(x j )]-occurring is limited, which immediately proves the theorem.…”

Section: Problem Descriptionmentioning

confidence: 84%

See 1 more Smart Citation

Robust and Reliable Vertical Handoff Technique for Next Generation Wireless Networks

Jayasheela¹,

Gowrishankar²

2018

EJERS

View full text Add to dashboard Cite

Next Generation Wireless Networks (NGWNs) focus on providing consistent Quality of Service (QoS) to network users; to achieve this goal, Cooperative Communication (CC) framework is popularly utilized. Here, multiple wireless networks cooperate to provide consistent QoS to the user. Vertical Handoff (VH) is one of the extensively used techniques in CC framework. Here, the user, whose original network is unable to provide requested QoS is migrated to neighboring wireless network--which can deliver the requested QoS. In the literature, raft of techniques have been presented for VH. However, almost all these techniques have ignored formal methods to analyze reliability and robustness of handoff decisions, which are extremely essential to support the merits of handoff decisions. In this work, formal methods to analyze reliability and robustness of handoff decisions are presented. The proposed VH technique is achieved through Long Short Term Memory (LSTM) architecture. Simulation results exhibit the relative merits of the proposed VH technique in-terms of reliability and robustness against contemporary VH technique.

show abstract

Section: Problem Descriptionmentioning

confidence: 84%

“…A. LSTM Overview LSTM [21]- [24] is a special version of Recurrent Neural Network (RNN). Sequential data, in many cases, contains correlations in different sections of the data.…”

Section: Vh Technique For Reliable and Robust Handoffmentioning

confidence: 99%

Robust and Reliable Vertical Handoff Technique for Next Generation Wireless Networks

Jayasheela¹,

Gowrishankar²

2018

EJERS

View full text Add to dashboard Cite

show abstract

“…For future developments we consider relevant testing of other behaviors, such trying to decoy the attackers to reveal their origins. IoT honeypots are used at large scale and there is a genuine interest in developing ways to pattern attackers' behavior [50][51][52]. The results are promising but still there is room for improvement, for example considering novel encryption schemes [53,54].…”

Section: Discussionmentioning

confidence: 99%

On the rewards of self-adaptive IoT honeypots

et al. 2019

View full text Add to dashboard Cite

In an era of fully digitally interconnected people and machines, IoT devices become a real target for attackers. Recent incidents such as the well-known Mirai botnet, have shown that the risks incurred are huge and therefore a risk assessment is mandatory. In this paper we present a novel approach on collecting relevant data about IoT attacks. We detail a SSH/Telnet honeypot system that leverages reinforcement learning algorithms in order to interact with the attackers, and we present the results obtained in view of defining optimal reward functions to be used. One of the key issues regarding the performance of such algorithms is the direct dependence on the reward functions used. The main outcome of our study is a full implementation of an IoT honeypot system that leverages Apprenticeship Learning using Inverse Reinforcement Learning, in order to generate best suited reward functions.

show abstract

“…Hidden Markov Models [12]. Here we apply recurrent neural networks, that were 1 http://www.disiem-project.eu/ also employed in cybersecurity tasks [13]. Recurrent Neural Networks (RNNs) [14] are a class of artificial neural network where neurons are stacked in a recursive manner.…”

Section: Related Workmentioning

confidence: 99%

System Misuse Detection Via Informed Behavior Clustering and Modeling

Adilova

Natious

Chen³

et al. 2019

2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)

View full text Add to dashboard Cite

One of the main tasks of cybersecurity is recognizing malicious interactions with an arbitrary system. Currently, the logging information from each interaction can be collected in almost unrestricted amounts, but identification of attacks requires a lot of effort and time of security experts. We propose an approach for identifying fraud activity through modeling normal behavior in interactions with a system via machine learning methods, in particular LSTM neural networks. In order to enrich the modeling with system specific knowledge, we propose to use an interactive visual interface that allows security experts to identify semantically meaningful clusters of interactions. These clusters incorporate domain knowledge and lead to more precise behavior modeling via informed machine learning. We evaluate the proposed approach on a dataset containing logs of interactions with an administrative interface of login and security server. Our empirical results indicate that the informed modeling is capable of capturing normal behavior, which can then be used to detect abnormal behavior.

show abstract

Application of Deep Recurrent Neural Networks for Prediction of User Behavior in Tor Networks

Cited by 22 publications

References 18 publications

Robust and Reliable Vertical Handoff Technique for Next Generation Wireless Networks

Robust and Reliable Vertical Handoff Technique for Next Generation Wireless Networks

On the rewards of self-adaptive IoT honeypots

System Misuse Detection Via Informed Behavior Clustering and Modeling

Contact Info

Product

Resources

About