Secure Automatic Identification System (SecAIS): Proof-of-Concept Implementation

Goudosis, Athanasios; Katsikas, Sokratis K.

doi:10.3390/jmse10060805

Cited by 4 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using this extensive dataset, our goal is to create models that can predict waiting times and turnaround times for ships at Haiphong Port. These forecasts are crucial to enable port authorities to coordinate operations, optimise resource allocation, and improve overall port efficiency [87][88][89].…”

Section: Case Studymentioning

confidence: 99%

Leveraging Artificial Intelligence to Enhance Port Operation Efficiency

Dinh,

Pham,

Nguyen

et al. 2024

Polish Maritime Research

View full text Add to dashboard Cite

Maritime transport forms the backbone of international logistics, as it allows for the transfer of bulk and long-haul products. The sophisticated planning required for this form of transportation frequently involves challenges such as unpredictable weather, diverse types of cargo kinds, and changes in port conditions, all of which can raise operational expenses. As a result, the accurate projection of a ship’s total time spent in port, and the anticipation of potential delays, have become critical for effective port activity planning and management. In this work, we aim to develop a port management system based on enhanced prediction and classification algorithms that are capable of precisely forecasting the lengths of ship stays and delays. On both the training and testing datasets, the XGBoost model was found to consistently outperform the alternative approaches in terms of RMSE, MAE, and R2 values for both the turnaround time and waiting period models. When used in the turnaround time model, the XGBoost model had the lowest RMSE of 1.29 during training and 0.5019 during testing, and also achieved the lowest MAE of 0.802 for training and 0.391 for testing. It also had the highest R2 values of 0.9788 during training and 0.9933 during testing. Similarly, in the waiting period model, the XGBoost model outperformed the random forest and decision tree models, with the lowest RMSE, MAE, and greatest R2 values in both the training and testing phases.

show abstract

Section: Case Studymentioning

confidence: 99%

Leveraging Artificial Intelligence to Enhance Port Operation Efficiency

Dinh,

Pham,

Nguyen

et al. 2024

Polish Maritime Research

View full text Add to dashboard Cite

show abstract

“…Goudossis et al (2019) proposed an authentication and integrity scheme for AIS, and in their follow-up work (Goudosis and Katsikas, 2020) addressed the implementation aspects of (Goudossis et al, 2019). Goudosis et al (2022) proposed secure automatic identification system (SecAIS) that provides the authentication, confidentiality, and anonymisation of AIS messages. Wimpenny et al (2022) proposed an elliptic curve based data integrity and authentication scheme for AIS.…”

Section: Related Workmentioning

confidence: 99%

“…AIS is an open standard and due to unauthenticated and unencrypted nature make it vulnerable to threats such as spoofing, hijacking, and availability disruption (Balduzzi et al, 2014) (Hall et al, 2015) (Khandker et al, 2022b) (Tran et al, 2021). To secure AIS, several security schemes have been proposed, including anonymous authentication schemes (Goudosis and Katsikas, 2022) (Jegadeesan et al, 2021), TESLA protocol-based scheme (Sciancalepore et al, 2021) and blockchain based schemes (Duan et al, 2022) (Freire et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Backward-compatible Software Upgrades for ADS-B and AIS To Support ECDSA-Secured Protocols

Saleem,

Turtiainen,

Costin

et al. 2024

eccws

View full text Add to dashboard Cite

During the past few decades, the aviation, maritime, aerospace, and search-and-rescue domains have witnessed tremendous improvement thanks to technological, digitalization and Internet of Things (IoT) advances such as Automatic Dependent Surveillance–Broadcast (ADS-B) (e.g., Aviation IoT, Airports IoT) and Automatic Identification System (AIS) (e.g., Maritime IoT). All these are high-profile examples of new digital communication protocols combined with IoT devices that make efficient use of wide-area earth and space radio communications to provide real-time, truly globally interoperable, and optimised services required by these domains. However, the protocols and technologies mentioned above, both from an architectural and implementation point of view, exhibit fundamental cybersecurity weaknesses (both at protocol and IoT device level). These weaknesses make them an easy target for potential attackers. The two fundamental flaws of these protocols are the lack of digital signatures (i.e., integrity and authenticity) and the lack of encryption (i.e., confidentiality and privacy). The risks associated with these, and other weaknesses have been over the last decade repeatedly demonstrated with ease by ethical cybersecurity researchers. In this paper, we design, propose, and discuss a single generic PKI-enabled message integrity and authenticity scheme that works seamlessly for any of the ADS-B, and AIS, with the possibility of easy extension and integration into other protocols (e.g., ACARS). Our scheme can be added as backward-compatible software upgrades (e.g., third-party library) to existing systems without requiring expensive architectural redesign, upgrades, and retrofitting. Our present work is aimed to serve as a bootstrap to securing such insecure protocols without completely replacing or redesigning the systems. It also aims to provide a discussion background of advantages and limitations of such backward-compatible securing methods.

show abstract