A Study of Identifying Attacks on Industry Internet of Things Using Machine Learning

2021 ◽  
Author(s):  
Chia-Mei Chen ◽  
Zheng-Xun Cai ◽  
Gu-Hsin Lai

The “Industry 4.0” revolution and Industry Internet of Things (IIoT) has dramatically transformed how manufacturing and industrial companies operate. Industrial control systems (ICS) process critical function, and the past ICS attacks have caused major damage and disasters in the communities. IIoT devices in an ICS environment communicate in heterogeneous protocols and the attack vectors might exhibit different misbehavior patterns. This study proposes a classification model to detect anomalies in ICS environments. The evaluation has been conducted by using ICS datasets from multiple sources and the results show that the proposed LSTM detection model performs effectively.

2018 ◽  
Vol 173 ◽  
pp. 01011 ◽  
Author(s):  
Xiaojun Zhou ◽  
Zhen Xu ◽  
Liming Wang ◽  
Kai Chen ◽  
Cong Chen ◽  
...  

With the arrival of Industry 4.0, more and more industrial control systems are connected with the outside world, which brings tremendous convenience to industrial production and control, and also introduces many potential security hazards. After a large number of attack cases analysis, we found that attacks in SCADA systems can be divided into internal attacks and external attacks. Both types of attacks are inevitable. Traditional firewalls, IDSs and IPSs are no longer suitable for industrial control systems. Therefore, we propose behavior-based anomaly detection and build three baselines of normal behaviors. Experiments show that using our proposed detection model, we can quickly detect a variety of attacks on SCADA (Supervisory Control And Data Acquisition) systems.


2019 ◽  
Vol 11 (1) ◽  
Author(s):  
Javier Echauz ◽  
Keith Kenemer ◽  
Sarfaraz Hussein ◽  
Jay Dhaliwal ◽  
Saurabh Shintre ◽  
...  

Machine learning models are vulnerable to adversarial inputs that induce seemingly unjustifiable errors. As automated classifiers are increasingly used in industrial control systems and machinery, these adversarial errors could grow to be a serious problem. Despite numerous studies over the past few years, the field of adversarial ML is still considered alchemy, with no practical unbroken defenses demonstrated to date, leaving PHM practitioners with few meaningful ways of addressing the problem. We introduce “turbidity detection” as a practical superset of the adversarial input detection problem, coping with adversarial campaigns rather than statistically invisible one-offs. This perspective is coupled with ROC-theoretic design guidance that prescribes an inexpensive domain adaptation layer at the output of a deep learning model during an attack campaign. The result aims to approximate the Bayes optimal mitigation that ameliorates the detection model’s degraded health. A proactively reactive type of prognostics is achieved via Monte Carlo simulation of various adversarial campaign scenarios, by sampling from the model’s own turbidity distribution to quickly deploy the correct mitigation during a real-world campaign.


Energies ◽  
2021 ◽  
Vol 14 (17) ◽  
pp. 5501
Author(s):  
Chenyang Liu ◽  
Yazeed Alrowaili ◽  
Neetesh Saxena ◽  
Charalambos Konstantinou

Cybersecurity threats targeting industrial control systems (ICS) have significantly increased in the past years. Moreover, the need for users/operators to understand the consequences of attacks targeting these systems and protect all assets is vital. This work explores asset discovery in ICS and how to rank these assets based on their criticality. This paper also discusses asset discovery and its components. We further present existing solutions and tools for asset discovery. We implement a method to identify critical assets based on their connection and discuss related results and evaluation. The evaluation utilises four attack scenarios to stress the importance of protecting these critical assets since the failure to protect them can lead to serious consequences. Using a 12-bus system case, our results show that targeting such a system can increase and overload transmission lines values to 120% and 181% MVA, which can affect the power supply and disrupt service, and it can increase the cost up to 60%, affecting the productivity of this electric grid.


2011 ◽  
Vol 216 ◽  
pp. 360-363 ◽  
Author(s):  
Jun Wang ◽  
Zhan Mei ◽  
Li Feng Wei

For further development and building a solid foundation of industrial Internet of things, a wireless communication card (WCC) based on UWB used in industrial Internet of Things (IoT) is designed in the paper. The implementations of WCC are proposed and critical problem on software design is solved. It successfully solves the problem of communication with IO card. At the same time, it provides upgrade program form industrial control systems to industrial Internet of Things.


Sign in / Sign up

Export Citation Format

Share Document