An adaptive immune based anomaly detection algorithm for smart WSN deployments

Salvato, M.; Vito, Saverio De; Guerra, Sara; Buonanno, Amedeo; Fattoruso, Grazia; Francia, G. Di

doi:10.1109/aisem.2015.7066840

Cited by 7 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A user may change their network environment in a legitimate way, such as changing their internet service provider or moving to another country; however, this may trigger a false alarm, the same as other round-trip based detection approaches. An automated update of the detection threshold to reflect the user's trends [48] and prompting the user to check whether it was legitimate authentication, via multi-factor authentication, would be effective ways of completing an adaptive detection system and minimizing false alarms.…”

Section: Discussionmentioning

confidence: 99%

Detecting Risky Authentication Using the OpenID Connect Token Exchange Time

Han,

Lee

2023

Sensors

View full text Add to dashboard Cite

With the rise in sophisticated cyber threats, traditional authentication methods are no longer sufficient. Risk-based authentication (RBA) plays a critical role in the context of the zero trust framework—a paradigm shift that assumes no trust within or outside the network. This research introduces a novel proposal as its core: utilization of the time required by OpenID Connect (OIDC) token exchanges as a new RBA feature. This innovative approach enables the detection of tunneled connections without any intervention from the user’s browser or device. By analyzing the duration of OIDC token exchanges, the system can identify any irregularities that may signify unauthorized access attempts. This approach not only improves upon existing RBA frameworks but is also in alignment with the broader movement toward intelligent and responsive security systems.

show abstract

Section: Discussionmentioning

confidence: 99%

Detecting Risky Authentication Using the OpenID Connect Token Exchange Time

Han,

Lee

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…As a result, for estimating the pH (or EC) values, the Kalman filter requires a total of six variables to be kept between calls: two for the state vector and four for the covariance matrix. In contrast to the algorithms proposed in [26,27,28], neither the run time nor the memory usage of our algorithm scale with the number of previously considered samples, making it more suitable for IoT resource-constraint devices.…”

Section: Algorithm 1 Real-time Anomaly Detection Algorithmmentioning

confidence: 93%

“…DBSCAN is also used in [25]. In our opinion, the immune base algorithm of Salvato et al not only detect abnormal measurements, but may also have the capability of identifying the type of chemical substances in a measurement, which unfortunately was not evaluated by Salvato et al in [26]. In our work, we provide an anomaly detection algorithm of lower running and memory complexity without the possibilities of substance identification.…”

Section: B Anomaly Detection Algorithms Based On Water Quality Parametersmentioning

confidence: 99%

“…The SIMONA sensor network nodes -refer to [17] and its reference in Table 2 -have implemented in-built clustering anomaly detection algorithms, proposed by Salvato et al in [26]. The immune based algorithms comprises two consecutive phases in its operational lifetime: a) a learning phase -where the DBSCAN algorithm [29] is used for clustering the first 200 measurements -and, b) a classification phasewhere new measurements are classified as normal or abnormal and the knowledge about the system is updated using immune based rules.…”

Section: B Anomaly Detection Algorithms Based On Water Quality Parametersmentioning

confidence: 99%

See 1 more Smart Citation

An Internet-of-Things Enabled Smart System for Wastewater Monitoring

2022

View full text Add to dashboard Cite

We present and evaluate an IoT-enabled sensing and actuating system for localizing illegal industrial harsh discharges of polluting wastewater in sewer networks. The special conditions of the sewer environment bring special challenges for the design of an IoT system and of its real-time algorithm for anomaly detection and localization in wastewater networks. The proposed design fulfills these requirements by using a new IoT architecture pattern, which we generalize and name Hop-by-hop Anomaly Detection and Actuation (HADA). The distributed anomaly detection and localization algorithm makes predictions over previous sensor measurements, while taking into account seasonality effects of wastewater and noise of the sensors. Based on simulations in a large network with three common illegal industrial wastewater pollutants, the advantages and limitations of the proposed wastewater anomaly localization system are discussed. The IoT system, including its anomaly detection and localization algorithm, was implemented using in a low-power microcontroller and tested in flowing wastewater with different harsh industrial waste.

show abstract

“…The ability of the immune system to cope with a dynamic environment is leveraged in [ 169 ]. In this work, the authors developed an anomaly detection approach inspired by the clonal selection found in the HIS.…”

Section: Literature Review On Immune-inspired Approachesmentioning

confidence: 99%

A Review on Immune-Inspired Node Fault Detection in Wireless Sensor Networks with a Focus on the Danger Theory

Widhalm

Goeschka

Kästner

2023

Sensors

View full text Add to dashboard Cite

The use of fault detection and tolerance measures in wireless sensor networks is inevitable to ensure the reliability of the data sources. In this context, immune-inspired concepts offer suitable characteristics for developing lightweight fault detection systems, and previous works have shown promising results. In this article, we provide a literature review of immune-inspired fault detection approaches in sensor networks proposed in the last two decades. We discuss the unique properties of the human immune system and how the found approaches exploit them. With the information from the literature review extended with the findings of our previous works, we discuss the limitations of current approaches and consequent future research directions. We have found that immune-inspired techniques are well suited for lightweight fault detection, but there are still open questions concerning the effective and efficient use of those in sensor networks.

show abstract

An adaptive immune based anomaly detection algorithm for smart WSN deployments

Cited by 7 publications

References 7 publications

Detecting Risky Authentication Using the OpenID Connect Token Exchange Time

Detecting Risky Authentication Using the OpenID Connect Token Exchange Time

An Internet-of-Things Enabled Smart System for Wastewater Monitoring

A Review on Immune-Inspired Node Fault Detection in Wireless Sensor Networks with a Focus on the Danger Theory

Contact Info

Product

Resources

About