Foundations of a CPS Resilience - October 2021

PI: Xenofon Koutsoukos

HARD PROBLEM(S) ADDRESSED

The goals of this project are to develop the principles and methods for designing and analyzing resilient CPS architectures that deliver required service in the face of compromised components. A fundamental challenge is to understand the basic tenets of CPS resilience and how they can be used in developing resilient architectures. The primary hard problem addressed is resilient architectures. In addition, the work addresses scalability and composability as well as metrics and evaluation. 

PUBLICATIONS

[1]    Dimitrios Boursinos and Xenofon Koutsoukos, “Reliable Probability Intervals for Classification Using Inductive Venn Predictors Based on Distance Learning”, IEEE International Conference on Omni-layer Intelligent systems (COINS 2021). August 23-25, 2021.

[2]    Feiyang Cai, Ali Ozdagli, Nicholas Potteiger, and Xenofon Koutsoukos. “Inductive Conformal Out-of-distribution Detection based on Adversarial Autoencoders”, IEEE International Conference on Omni-layer Intelligent systems (COINS 2021). August 23-25, 2021.

[3]    Himanshu Neema, Leqiang Wang, Xenofon Koutsoukos, CheeYee Tang, and Keith Stouffer, “Model-Based Risk Analysis Approach for Network Vulnerability and Security of the Critical Railway Infrastructure”, The 16th International Conference on Critical Information Infrastructures Security (CRITIS 2021). September 27-29, 2021.
 

KEY HIGHLIGHTS

This quarterly report presents two key highlight that demonstrate: (1) an algorithm for reliable probability intervals for classification evaluated on botnet attacks detection in Internet-of-Things (IoT) applications and (2) and approach for inductive conformal out-of-distribution detection based on adversarial autoencoders.

Highlight 1: Reliable Probability Intervals for Classification

Deep neural networks are frequently used by autonomous systems for their ability to learn complex, non-linear data patterns and make accurate predictions in dynamic environments. However, their use as black boxes introduces risks as the confidence in each prediction is unknown. Different frameworks have been proposed to compute accurate confidence measures along with the predictions but at the same time limitations such as execution time overhead or inability to be used with high-dimensional data. In this paper, we use Inductive Venn Predictors for computing probability intervals regarding the correctness of each prediction in real-time. We propose taxonomies based on distance metric learning to compute informative probability intervals in applications involving high-dimensional inputs. Empirical evaluation on botnet attacks detection in Internet-of-Things (IoT) applications demonstrates improved accuracy and calibration. The proposed method is computationally efficient, and therefore, can be used in real-time. Our results are presented in [1]. 

[1]    Dimitrios Boursinos and Xenofon Koutsoukos, “Reliable Probability Intervals for Classification Using Inductive Venn Predictors Based on Distance Learning”, IEEE International Conference on Omni-layer Intelligent systems, (COINS 2021). August 23-25, 2021.

Highlight 2: Inductive Conformal Out-of-distribution Detection

Machine learning components are used extensively to cope with various complex tasks in highly uncertain environments. However, Out-Of-Distribution (OOD) data may lead to predictions with large errors and degrade performance considerably. This paper first introduces different types of OOD data and then presents an approach for OOD detection for classification problems efficiently. Our approach utilizes an Adversarial Autoencoder (AAE) for representing the training distribution and Inductive Conformal Anomaly Detection (ICAD) for online detecting OOD high-dimensional data. Experimental results using several datasets demonstrate that the approach can detect various types of OOD data with a small number of false alarms. Moreover, the execution time is very short, allowing for online detection. Our results are presented in [2]. 

[2]   Feiyang Cai, Ali Ozdagli, Nicholas Potteiger, and Xenofon Koutsoukos. “Inductive Conformal Out-of-distribution Detection based on Adversarial Autoencoders”, IEEE International Conference on Omni-layer Intelligent systems, (COINS 2021). August 23-25, 2021.