An LSTM-autoencoder based online side channel monitoring approach for cyber-physical attack detection in additive manufacturing

Shi, Zhangyue; Mamun, Abdullah Al; Chen, Kan; Tian, Wenmeng; Liu, Chenang

doi:10.1007/s10845-021-01879-9

Cited by 35 publications

(8 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hash function, also known as the hash function, its functional feature is that it can output fixed length summary information after a series of changes and processing of an unlimited length message, and the resulting summary result is called a hash value [10,5]. The hash function has unidirectionality, meaning that its encryption process is easily implemented in a computer, while the decryption process is not feasible in a computer.…”

Section: Sm3 Password Hash Algorithmmentioning

confidence: 99%

Intelligent Detection and Analysis of Software Vulnerabilities based on Encryption Algorithms and Feature Extraction

Li,

Wei

2024

SCPE

View full text Add to dashboard Cite

Implement status detection of ship software, identify the source of faults in problematic software, and release new software versions. Based on the above requirements, the author regards the detection and control of ship software status as the core research content. Based on the actual operating environment of ship software, the functional requirements of software status detection were studied and analyzed, and a set of ship software status detection was designed and implemented, a software inspection and maintenance platform that integrates ship software operation and maintenance, as well as ship software version release and update. The author conducted practical verification of the SM3 and SM2 hybrid encryption algorithm and selected software on the ship for detection. After analyzing the experimental results, it has been proven that using a hybrid algorithm for encryption and decryption, the server can accurately obtain software information on the ship's platform, detect the software status on the ship, and locate specific problem files. For software that does not meet the standard status, the server can accurately transmit software information to the ``component integration framework'' and put the component in a ``prohibited'' scheduling state. After the server repairs the problematic software, the detection results of the software change and display as legal, while the software is in the ``allowed'' scheduling state in the ``component integration framework''.

show abstract

Section: Sm3 Password Hash Algorithmmentioning

confidence: 99%

Intelligent Detection and Analysis of Software Vulnerabilities based on Encryption Algorithms and Feature Extraction

Li,

Wei

2024

SCPE

View full text Add to dashboard Cite

show abstract

“…In-situ monitoring is largely applied in AM for defect and anomaly detection. Sensors 118,190 and high-resolution cameras 189,192,195 are commonly used to detect defects in real-time. Data acquired from sensor signals and processed images are often combined with ML techniques for predicting defects in the early stages of printing process.…”

Section: In-situ Monitoringmentioning

confidence: 99%

Application of machine learning in polymer additive manufacturing: A review

Nasrin,

Pourkamali‐Anaraki,

Peterson

2023

Journal of Polymer Science

View full text Add to dashboard Cite

Additive manufacturing (AM) is a revolutionary technology that enables production of intricate structures while minimizing material waste. However, its full potential has yet to be realized due to technical challenges such as the dependence of part quality on numerous process parameters, the vast number of design options, and the occurrence of defects. These complications may be magnified by the use of polymers and polymer composites due to their complex molecular structures, batch‐to‐batch variations, and changes in final part properties caused by small alterations in process settings and environmental conditions. Machine learning (ML), a branch of artificial intelligence, offers approaches to tackle these challenges and significantly reduce the experimental and computational time and expense. This review provides a comprehensive analysis of existing research on integrating ML techniques into polymer AM. It highlights the challenges involved in adopting ML in polymer AM, proposes potential solutions, and identifies areas for future research.

show abstract

“…As observed in this work, the method based on audio signal requires less expensive installation, but it is more sensitive to the background noise, thus making the method based on video stream preferable in long run. Cyberattack detection in additive manufacturing based on vibration signal was also explored [26], where the features extracted using LSTM (long short-term memory recurrent neural networks) based autoencoder were employed.…”

Section: Cybersecurity Challenges In Distributed Motion Controlmentioning

confidence: 99%

Cybersecurity Issues in Motion Control – An Overview of Challenges

Jakovljević

Nedeljković

2023

2023 10th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN)

View full text Add to dashboard Cite

The fourth industrial revolution known as Industry 4.0 brings digitalization of manufacturing processes to a new level through ubiquitous interconnection and real-time information flow between information technologies (IT) and operational technologies (OT) as parts of Industrial Control Systems (ICS). This information flow is not limited to but expands beyond factory walls enabling manufacturing systems to adapt quickly and efficiently to changing customer demands and diversified products. The adaptation is carried out through physical and/or functional reconfiguration of manufacturing systems where Industrial Internet of Things (IIoT) based on Cyber-Physical Systems (CPS) represents the key technical enabler. These changes result in a transition from centralized to distributed control systems architecture where the whole control task is achieved through intensive cooperation between smart devices (e.g., sensors and actuators) with integrated communication and computation capabilities. However, introducing IIoT in ICS brings about new cybersecurity issues due to increased communication between system elements and connection to the global network, making ICS vulnerable to different cyber-attacks with potentially catastrophic consequences. Recently, the research in ICS cybersecurity has intensified leading to significant results for continuous time and discrete events-controlled systems. However, cybersecurity issues in motion control systems that are frequently employed in different manufacturing resources such as machine tools and industrial robots were not sufficiently explored. This work provides an overview of the cybersecurity related challenges in motion control tasks.

show abstract

An LSTM-autoencoder based online side channel monitoring approach for cyber-physical attack detection in additive manufacturing

Cited by 35 publications

References 61 publications

Intelligent Detection and Analysis of Software Vulnerabilities based on Encryption Algorithms and Feature Extraction

Intelligent Detection and Analysis of Software Vulnerabilities based on Encryption Algorithms and Feature Extraction

Application of machine learning in polymer additive manufacturing: A review

Cybersecurity Issues in Motion Control – An Overview of Challenges

Contact Info

Product

Resources

About