Radu Babiceanu

Dr. Radu Babiceanu

Department of Electrical Engineering and Computer Science, Embry-Riddle Aeronautical University, Daytona Beach, FL, USA

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 April 2021
Verified
Conference Paper
Closed access
AGAnna Baron Garcia
Anna Baron Garcia
RBRadu Babiceanu
Radu Babiceanu
RSRemzi Seker
Remzi Seker
Artificial Intelligence (AI) and Machine Learning (ML) applications are currently found across all engineering domains, including cybersecurity engineering. This paper presents an overview of the AI-systems and technologies that can greatly benefit the security domain and its potential solutions for the aviation industry: anomaly detection for avionics, securing data link communications, and security certification, among others.As showcased in the "National Strategy for Aviation Security" report in December 2018 and the U.S. Government Accountability Office report "Aviation Cybersecurity" in October 2020, there is a need for resilient cybersecurity practices and approaches to address the current issues that aviation faces today. Designing and implementing solutions to address these issues without exploring the feasibility of harnessing AI-powered cybersecurity tools would overlook the potential advantages these technologies can offer.Therefore, this paper aims to provide a roadmap to adapt well-known ML-cybersecurity approaches to aviation security engineering and airworthiness: (i) autonomous and semi-autonomous cybersecurity for autonomous flight operations security, (ii) game theory models for adversarial and uncertainty modeling, (iii) human-AI interfaces for airport security monitoring and decision-making assistance, (iv) predictive analytics for anomaly detection for avionics and e-enabled aircraft, and (v) AI-based reasoning trustworthiness for software reliability and security certification. This paper also presents the challenges of including AI-cybersecurity in the aviation ecosystem to ground the proposed solutions within an accepted set of industry regulations, such as design verification for AI/ML algorithms and certification specifications for AI/ML solutions for manufacturers and agencies.

15 October 2019 in Journal of Intelligent Manufacturing
Verified
Journal Article
Closed access
PDF file
SJShashi Bhushan Jha
Shashi Bhushan Jha
RBRadu Babiceanu
Radu Babiceanu
RSRemzi Seker
Remzi Seker

1 April 2016
Verified
Conference Paper
Closed access
JSJessica A. Steinmann
Jessica A. Steinmann
RBRadu Babiceanu
Radu Babiceanu
RSRemzi Seker
Remzi Seker
Unmanned aerial systems, often referred as drones, are becoming largely popular among general public and businesses. The system includes the actual unmanned aerial system (UAS), the ground station and the communication link between them. The data transmitted between the ground station and the UAS in both directions, as well as the data stored on the UAS memory chips in the case of a crash or an illegitimate access to it, should not be easily available to a third party. This paper proposes an encryption key negotiation method for partitioned data stored and exchanged in UAS applications. The proposed approach, aimed at providing authentication and security through key negotiation, includes a modified cryptographic protocol that uses a combination of off-the-record and pretty good privacy to encrypt the data stored on UAS and the data transmitted through the communication link between the ground station and the UAS. The encryption solutions were tested using a Java environment and are proposed to be implemented on FPGA development boards to be installed on prototype UAS. Depending on the encryption method used AES/RSA and the computational requirements, the cost of an actual implementation may increase due to the need of faster FPGA chips.