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

Abstract Due to its predominant flexibility in fabricating complex geometries, additive manufacturing (AM) has gain increasing popularity in various mission critical applications, such as aerospace, health care, military, and transportation. The layerby-layer manner of AM fabrication significantly expands the vulnerability space of AM cyber-physical systems, leading to potentially altered AM parts with compromised mechanical properties and functionalities. Moreover, internal alterations of the build are very difficult to detect based on traditional geometric dimensioning and tolerancing (GD&T) features. Therefore, how to achieve effective monitoring and attack detection is a very important problem for broader adoption of AM technology. To address this issue, this paper proposes to utilize side channels for process authentication. An online feature extraction approach is developed based on autoencoder to detect unintended process/product alterations caused by cyber-physical attacks. Both supervised and unsupervised monitoring schemes are implemented based on the extracted features. To validate the effectiveness of the proposed method, two real-world case studies are conducted on a fused filament fabrication (FFF) platform equipped with two accelerometers for process monitoring. Two different types of attacks are implemented. The results demonstrate that the proposed method outperforms conventional process monitoring methods, and can effectively detect part geometry and layer thickness alterations in real time.

Download Full-text

A Probe into Process-Level Attack Detection in Industrial Environments from a Side-Channel Perspective

Proceedings of the Fifth Annual Industrial Control System Security (ICSS) Workshop on - ICSS ◽

10.1145/3372318.3372320 ◽

2019 ◽

Author(s):

Wissam Aoudi ◽

Albin Hellqvist ◽

Albert Overland ◽

Magnus Almgren

Keyword(s):

Attack Detection ◽

Side Channel ◽

Industrial Environments ◽

Process Level

Download Full-text

Cyber—Physical Attack Detection in Water Distribution Systems with Temporal Graph Convolutional Neural Networks

Water ◽

10.3390/w13091247 ◽

2021 ◽

Vol 13 (9) ◽

pp. 1247

Author(s):

Lydia Tsiami ◽

Christos Makropoulos

Keyword(s):

Neural Networks ◽

Distribution System ◽

Distribution Systems ◽

Water Distribution ◽

Attack Detection ◽

Convolutional Network ◽

Irreversible Damage ◽

Physical Attack ◽

Temporal Graph ◽

Graph Neural Networks

Prompt detection of cyber–physical attacks (CPAs) on a water distribution system (WDS) is critical to avoid irreversible damage to the network infrastructure and disruption of water services. However, the complex interdependencies of the water network’s components make CPA detection challenging. To better capture the spatiotemporal dimensions of these interdependencies, we represented the WDS as a mathematical graph and approached the problem by utilizing graph neural networks. We presented an online, one-stage, prediction-based algorithm that implements the temporal graph convolutional network and makes use of the Mahalanobis distance. The algorithm exhibited strong detection performance and was capable of localizing the targeted network components for several benchmark attacks. We suggested that an important property of the proposed algorithm was its explainability, which allowed the extraction of useful information about how the model works and as such it is a step towards the creation of trustworthy AI algorithms for water applications. Additional insights into metrics commonly used to rank algorithm performance were also presented and discussed.

Download Full-text

CloudRadar: A Real-Time Side-Channel Attack Detection System in Clouds

Research in Attacks, Intrusions, and Defenses - Lecture Notes in Computer Science ◽

10.1007/978-3-319-45719-2_6 ◽

2016 ◽

pp. 118-140 ◽

Cited By ~ 51

Author(s):

Tianwei Zhang ◽

Yinqian Zhang ◽

Ruby B. Lee

Keyword(s):

Real Time ◽

Detection System ◽

Attack Detection ◽

Side Channel ◽

Side Channel Attack

Download Full-text

Fault Attack Detection in AES by Monitoring Power Side-Channel Statistics

2020 21st International Symposium on Quality Electronic Design (ISQED) ◽

10.1109/isqed48828.2020.9136981 ◽

2020 ◽

Cited By ~ 1

Author(s):

Ahish Shylendra ◽

Priyesh Shukla ◽

Swarup Bhunia ◽

Amit Ranjan Trivedi

Keyword(s):

Attack Detection ◽

Side Channel ◽

Fault Attack ◽

Channel Statistics

Download Full-text

A Blockchain-based G-code Protection Approach for Cyber-Physical Security in Additive Manufacturing

Journal of Computing and Information Science in Engineering ◽

10.1115/1.4048966 ◽

2020 ◽

pp. 1-29

Author(s):

Zhangyue Shi ◽

Chen Kan ◽

Wenmeng Tian ◽

Chenang Liu

Keyword(s):

Additive Manufacturing ◽

Data Storage ◽

Real World ◽

Physical Security ◽

Physical Attack ◽

Real World Applications ◽

The Face ◽

G Code ◽

Code Security ◽

Intellectual Property Theft

Abstract As an emerging technology, additive manufacturing (AM) is able to fabricate products with complex geometries using various materials. In particular, cyber-enabled AM systems have recently become widely applied in many real-world applications. It significantly improves the flexibility and productivity of AM but poses the system under high risks of cyber-physical attacks. For example, cyber-physical attack could maliciously tamper the product design and process parameters, which, in turn, leads to significant alteration of the desired properties in AM products. Therefore, there is an urgent need in incorporating advanced technologies to improve the cyber-physical security for the cyber-enabled AM systems. In this study, two common types of cyber-physical attacks regarding the G-code security were investigated, namely, unintended design modifications and intellectual property theft. To effectively secure the G-code against these two attacks, a new methodology is developed in this study, which consists of a novel blockchain-based data storage approach and an effective asymmetry encryption technique. The proposed method was also applied to a real-world AM case for ensuring the cyber-physical security of the face shield fabrication, which is critical during the COVID-19 pandemic. Based on the proposed methodology, malicious tampering can be accurately detected in a timely manner and meanwhile the risk of unauthorized access of the G-code file will be greatly eliminated as well.

Download Full-text